© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    names of companies

    oai_token-act-pair · gemini-2.0-flash

    technical terms and identifiers

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

    commas and periods

    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
    artig
    -0.49
    ukkah
    -0.48
    quiel
    -0.45
    bės
    -0.45
    atum
    -0.45
    Glyph
    -0.44
     Raf
    -0.43
     Multi
    -0.43
     sil
    -0.42
    oli
    -0.42
    POSITIVE LOGITS
    featureID
    0.81
    ThroughAttribute
    0.68
    enterOuterAlt
    0.62
    EDEFAULT
    0.59
    MLLoader
    0.59
    ^(@)
    0.58
    EndInit
    0.57
    vertida
    0.56
    RTGC
    0.56
    GOTREF
    0.55
    Activations Density 0.862%

    No Known Activations