© 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. 13970
    Prev
    Next
    INDEX
    Explanations

    commas preceded by a word and followed by the word "previous" or "in fact"

    oai_token-act-pair · gemini-2.0-flash

    commas

    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
     Paglinawan
    -0.84
     createContext
    -0.82
     ostavi
    -0.81
     للمعارف
    -0.81
    IntoConstraints
    -0.77
    tonsoft
    -0.76
    principalColumn
    -0.75
    expandindo
    -0.73
    DeleteBehavior
    -0.73
    lgari
    -0.71
    POSITIVE LOGITS
    <bos>
    0.85
     the
    0.60
    μισ
    0.53
     
    0.49
    ↵
    0.45
     tuturor
    0.44
    1
    0.44
    The
    0.43
     be
    0.43
     ripar
    0.42
    Activations Density 1.343%

    No Known Activations