© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7840
    Prev
    Next
    INDEX
    Explanations

    commas within text

    oai_token-act-pair · gemini-2.0-flash

    comma punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     also
    -0.52
     ALSO
    -0.52
    also
    -0.51
     consider
    -0.50
     find
    -0.48
     tambien
    -0.48
     também
    -0.47
     betre
    -0.47
     също
    -0.47
     remember
    -0.47
    POSITIVE LOGITS
    <bos>
    0.88
     Paglinawan
    0.76
     Infórmanos
    0.73
     ſmall
    0.69
     houſe
    0.69
     Monfieur
    0.68
     perſon
    0.67
     myſelf
    0.66
    tvguidetime
    0.65
     Gorb
    0.64
    Activations Density 2.349%

    No Known Activations