© 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. 6351
    Prev
    Next
    INDEX
    Explanations

    words that denote situations that are difficult or unusual

    oai_token-act-pair · gemini-2.0-flash

    specialized terms or jargon

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

    negative situations

    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
     strange
    -0.66
     favorable
    -0.60
     interesting
    -0.58
     weird
    -0.57
     bad
    -0.57
     terrible
    -0.56
     favourable
    -0.56
     fantastic
    -0.55
     bizarre
    -0.54
     unusual
    -0.54
    POSITIVE LOGITS
     فريبيس
    0.90
     للاسماء
    0.89
    Hochspringen
    0.76
    VersionUID
    0.74
    MLLoader
    0.74
    出版年
    0.71
    WithMany
    0.71
    DataAnnotations
    0.70
     flesta
    0.70
    ValueStyle
    0.68
    Activations Density 2.613%

    No Known Activations