© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3253
    Prev
    Next
    INDEX
    Explanations

    mentions the word "hit" when it means to be harmed or for something to badly affect a person.

    oai_token-act-pair · gemini-2.0-flash

    stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     mergeFrom
    -0.65
    SharedCtor
    -0.48
    brigens
    -0.46
    %</
    -0.46
     volon
    -0.46
     /\.
    -0.46
    ってみました
    -0.46
     accessoire
    -0.46
     pourtant
    -0.44
     />';
    -0.44
    POSITIVE LOGITS
    NoSuchAlgorithm
    0.77
    zzleHttp
    0.74
     defaultstate
    0.69
    ligible
    0.68
     ineligible
    0.66
    AndEndTag
    0.66
     للمعارف
    0.66
     initComponents
    0.65
     plowed
    0.65
    UnsafeEnabled
    0.65
    Activations Density 1.529%

    No Known Activations