© 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. 8304
    Prev
    Next
    INDEX
    Explanations

    addresses or references to places

    oai_token-act-pair · gemini-2.0-flash

    archaic/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_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
    /***/
    -0.46
    脚注の使い方
    -0.45
    ussch
    -0.45
    municipi
    -0.44
    lik
    -0.43
    sizeCache
    -0.43
    ich
    -0.41
    TabIndex
    -0.39
    sto
    -0.39
    tvguidetime
    -0.39
    POSITIVE LOGITS
     raiſ
    0.87
     myſelf
    0.85
     pleaſure
    0.85
     Monfieur
    0.82
     faſt
    0.80
     itſelf
    0.79
     ſeveral
    0.75
     himſelf
    0.75
     leaſt
    0.74
     ſhe
    0.73
    Activations Density 0.924%

    No Known Activations