© 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. 12966
    Prev
    Next
    INDEX
    Explanations

    words related to cosmetic procedures and legal advice.

    oai_token-act-pair · gemini-2.0-flash

    cosmetic procedures

    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
    AccessorTable
    -0.78
     SqlDbType
    -0.67
    setVerticalGroup
    -0.65
    ophone
    -0.63
     jspb
    -0.63
    ponents
    -0.60
    PONENT
    -0.60
    RegistryLite
    -0.60
     AssemblyProduct
    -0.59
    bindingNavigator
    -0.59
    POSITIVE LOGITS
    <bos>
    1.34
    '
    0.47
     виправивши
    0.44
     getItemId
    0.40
     ExecuteAsync
    0.40
    -
    0.40
    álló
    0.40
    <
    0.39
    X
    0.39
    x
    0.38
    Activations Density 1.646%

    No Known Activations