© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13156
    Prev
    Next
    INDEX
    Explanations

    words ending in "ical" or "types" and that are related to classifying things

    oai_token-act-pair · gemini-2.0-flash

    ical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     protection
    -0.56
    Enllaços
    -0.50
    Protection
    -0.50
     L
    -0.49
    protection
    -0.48
     protected
    -0.47
    ah
    -0.47
    noscript
    -0.46
    protected
    -0.46
     Protección
    -0.45
    POSITIVE LOGITS
     typique
    0.73
    voorbeeld
    0.70
     Signalez
    0.68
     CreateTagHelper
    0.66
    typal
    0.64
    ſelf
    0.64
    出版年
    0.63
     REPRESENTATIVES
    0.63
    ScopeManager
    0.63
     típico
    0.63
    Activations Density 1.698%

    No Known Activations