© 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. 16270
    Prev
    Next
    INDEX
    Explanations

    capitalized proper nouns and titles, particularly last names

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     MainAxisSize
    -0.57
    IsContent
    -0.42
     OnInit
    -0.38
    RenderAtEndOf
    -0.36
     vulgaires
    -0.34
    bootstrapcdn
    -0.33
    хьтан
    -0.32
    toHexString
    -0.32
    ="@+
    -0.31
     nevo
    -0.31
    POSITIVE LOGITS
    -
    0.99
    <bos>
    0.63
    gaard
    0.58
    teries
    0.58
    aloo
    0.57
    -​
    0.57
    hoy
    0.56
    hurst
    0.55
    -...
    0.55
    ppan
    0.54
    Activations Density 6.887%

    No Known Activations