© 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. 7348
    Prev
    Next
    INDEX
    Explanations

    words related to emotion, judgement, or opinion

    oai_token-act-pair · gemini-2.0-flash

    related to speaking

    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
    CrossRef
    -0.45
    Proof
    -0.42
     Proof
    -0.42
     proof
    -0.42
     Assumption
    -0.41
    ciler
    -0.41
     signes
    -0.40
    ceae
    -0.40
    ANDE
    -0.39
    HtmlAttribute
    -0.39
    POSITIVE LOGITS
     says
    1.85
     Says
    1.65
    says
    1.63
     speak
    1.59
     speaks
    1.56
    Says
    1.55
     say
    1.55
     tells
    1.49
    say
    1.45
     SAYS
    1.43
    Activations Density 3.665%

    No Known Activations