© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15262
    Prev
    Next
    INDEX
    Explanations

    contexts describing social control, especially related to behaviors of children.

    oai_token-act-pair · gemini-2.0-flash

    terms related to difficulty or challenges

    np_token-act-pair-logits · gpt-4o-mini

    Difficult situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DECREF
    -0.58
    ArgsConstructor
    -0.57
    HasAnnotation
    -0.56
    TargetException
    -0.54
    silian
    -0.52
    ftagPool
    -0.45
    waitKey
    -0.45
    SuccessListener
    -0.45
     Nieto
    -0.44
    ModelBuilder
    -0.44
    POSITIVE LOGITS
     recal
    0.86
    difficult
    0.71
    abestanden
    0.71
    ThroughAttribute
    0.69
     difficult
    0.68
     Difficult
    0.68
     troublesome
    0.65
     vanske
    0.64
    Difficult
    0.63
     MainAxisSize
    0.63
    Activations Density 3.129%

    No Known Activations