© 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. 7824
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, especially relating to the variable kappa and the words 'in', 'ex', 'esc', 'lc', 'red' and 'X' when used as a mathematical variable.

    oai_token-act-pair · gemini-2.0-flash

    say "}" words

    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
     Efq
    -0.98
     myſelf
    -0.84
     Jefus
    -0.82
     pleaſure
    -0.81
     uſe
    -0.80
     Theſe
    -0.80
     raiſ
    -0.78
     Monfieur
    -0.78
     Reſ
    -0.77
     ſeveral
    -0.77
    POSITIVE LOGITS
    C
    0.59
    H
    0.57
    S
    0.55
    V
    0.55
    RG
    0.54
    dg
    0.54
    D
    0.54
    F
    0.54
    DG
    0.53
    L
    0.52
    Activations Density 9.021%

    No Known Activations