© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13081
    Prev
    Next
    INDEX
    Explanations

    bracketed expressions containing the word "fig" or "table" and some numbers after "p", "g", or "t".

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RegistryLite
    -0.71
     typelib
    -0.55
     通販
    -0.52
    -
    -0.52
    awtextra
    -0.52
     sentidos
    -0.51
     ordine
    -0.50
    -${
    -0.48
     bảng
    -0.47
    *-*-
    -0.47
    POSITIVE LOGITS
     houſe
    0.73
     Efq
    0.65
     Houſe
    0.64
     ContentValues
    0.62
     chofe
    0.59
     neceff
    0.59
    ?')
    0.58
    NonQuery
    0.58
     greateſt
    0.58
     pleaſure
    0.57
    Activations Density 3.600%

    No Known Activations