© 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. 6256
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    oai_token-act-pair · gemini-2.0-flash

    tokens with linguistic or numeric symbols

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

    comma

    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
     houſe
    -0.68
     fubject
    -0.67
     Jefus
    -0.66
     Chriftian
    -0.66
     Theſe
    -0.65
     Monfieur
    -0.65
     xenia
    -0.64
     ſtate
    -0.64
     ejus
    -0.62
     Italij
    -0.61
    POSITIVE LOGITS
    ôles
    0.52
    っこう
    0.51
     Ko
    0.51
     memas
    0.49
    boten
    0.47
     li
    0.47
     ten
    0.47
    lained
    0.47
     then
    0.46
    transQ
    0.46
    Activations Density 0.584%

    No Known Activations