© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3755
    Prev
    Next
    INDEX
    Explanations

    the word "claim" or the french word "que" in addition to other seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    legal claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    帖最后由
    -0.70
     Levine
    -0.59
    VERTICAL
    -0.57
     Vertical
    -0.56
     sorte
    -0.54
    bellar
    -0.54
    μως
    -0.53
    horizontal
    -0.53
     ProtoMessage
    -0.53
     vertical
    -0.53
    POSITIVE LOGITS
    <bos>
    0.79
     nonché
    0.60
    sowie
    0.60
    ."));
    0.58
     valamint
    0.58
    .";
    0.54
     sekä
    0.54
    Portail
    0.53
    ScopeManager
    0.52
    MLLoader
    0.51
    Activations Density 0.586%

    No Known Activations