© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7882
    Prev
    Next
    INDEX
    Explanations

    titles of TV shows and movies, especially those starting with "The"

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    InjectAttribute
    -0.56
    Rüyada
    -0.55
    FieldBuilder
    -0.53
    bbene
    -0.49
     تضيفلها
    -0.49
    roidery
    -0.49
    )");
    -0.48
     pData
    -0.47
    psies
    -0.47
    tonsoft
    -0.46
    POSITIVE LOGITS
     Superhost
    0.62
    catraz
    0.60
     Superhero
    0.60
     Warriors
    0.59
     Kombat
    0.58
    assination
    0.57
     Reverso
    0.53
     Exor
    0.52
     pauvres
    0.51
     الرياضيه
    0.50
    Activations Density 2.051%

    No Known Activations