© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6157
    Prev
    Next
    INDEX
    Explanations

    sentences that provide helpful context for image searches

    oai_token-act-pair · gemini-2.0-flash

    general website information or recommendations

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

    technical documentation and lists

    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
     Theſe
    -0.83
     Monfieur
    -0.81
    DockStyle
    -0.79
    RenderAtEndOf
    -0.77
     <=",
    -0.77
     Jefus
    -0.76
     Beſ
    -0.75
     Majefty
    -0.73
     myſelf
    -0.73
     themſelves
    -0.72
    POSITIVE LOGITS
     all
    0.53
     double
    0.52
    EnableWeb
    0.50
     الاجتما
    0.49
    ao
    0.47
    ä
    0.47
    IO
    0.47
     of
    0.47
    llo
    0.46
     re
    0.46
    Activations Density 0.338%

    No Known Activations