© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    opinions and judgements, including "is" and "was" statements

    oai_token-act-pair · gemini-2.0-flash

    Negative sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Autoritní
    -0.59
     voeten
    -0.50
    égard
    -0.48
    onViewCreated
    -0.48
    GOTREF
    -0.47
    pag
    -0.46
     compro
    -0.46
     Sak
    -0.46
    hell
    -0.46
    quin
    -0.46
    POSITIVE LOGITS
     Normdatei
    0.90
    ThroughAttribute
    0.76
     cherchés
    0.73
     Roskov
    0.66
    StructEnd
    0.65
    utilisons
    0.64
    dafx
    0.63
    MemoryWarning
    0.60
    Gweler
    0.59
    CPtr
    0.58
    Activations Density 2.118%

    No Known Activations