© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8424
    Prev
    Next
    INDEX
    Explanations

    words related to modifying things to suit certain conditions or preferences

    oai_token-act-pair · gemini-2.0-flash

    modifications and adjustments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -1.24
    TypedDataSet
    -0.97
    脚注の使い方
    -0.89
    Hochspringen
    -0.83
    __*/
    -0.82
    BeginInit
    -0.82
    protoimpl
    -0.80
    EndInit
    -0.80
    ValueStyle
    -0.80
     CURIAM
    -0.79
    POSITIVE LOGITS
     to
    1.48
    to
    0.63
    toBe
    0.49
    tothe
    0.49
     back
    0.47
     To
    0.47
     ot
    0.40
     να
    0.40
     Back
    0.39
    ToAction
    0.39
    Activations Density 3.793%

    No Known Activations