© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    oai_token-act-pair · gemini-2.0-flash

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Dacă
    -0.57
    rrggbb
    -0.56
    httphttps
    -0.53
    mektedir
    -0.50
     fresher
    -0.49
    ノブ
    -0.48
     vectorielle
    -0.48
     Bern
    -0.47
    kung
    -0.47
     dacă
    -0.47
    POSITIVE LOGITS
    withIdentifier
    0.71
     SqlConnection
    0.59
    WithIdentifier
    0.57
     DPRD
    0.57
    twimg
    0.53
     OkHttpClient
    0.52
    허
    0.51
     onAnimation
    0.51
     SQLAlchemy
    0.51
    ValueStyle
    0.51
    Activations Density 5.390%

    No Known Activations