© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13488
    Prev
    Next
    INDEX
    Explanations

    whitespace and commas and possibly some other punctuation

    oai_token-act-pair · gemini-2.0-flash

    tokens with commas or associated with specific language patterns

    np_token-act-pair-logits · gpt-4o-mini

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     juſ
    -0.68
     poffible
    -0.68
     uſe
    -0.66
     poffe
    -0.66
     purpoſe
    -0.65
     perſon
    -0.63
     Majefty
    -0.63
     pleaſure
    -0.63
     ſche
    -0.62
     myſelf
    -0.62
    POSITIVE LOGITS
     consultato
    0.62
     Italijani
    0.61
    govina
    0.56
     gynhyrchwyd
    0.55
    gió
    0.53
    gia
    0.53
     ivelany
    0.52
    Jeografia
    0.52
    UnsafeEnabled
    0.52
     ddelweddau
    0.50
    Activations Density 1.351%

    No Known Activations