© 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. 11387
    Prev
    Next
    INDEX
    Explanations

    mentions of "risk."

    oai_token-act-pair · gemini-2.0-flash

    terms related to risk assessment

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

    risk

    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
    setVerticalGroup
    -0.67
    Personensuche
    -0.62
    gameserver
    -0.60
    fromnode
    -0.57
    ConstraintMaker
    -0.56
    
    -0.56
    éroport
    -0.55
     disambiguazione
    -0.54
     مرئيه
    -0.54
    Loco
    -0.54
    POSITIVE LOGITS
    __;
    0.48
     profile
    0.45
    EDEFAULT
    0.44
    getragen
    0.44
     Med
    0.43
    profile
    0.43
     Cla
    0.42
    曜
    0.42
    zugehen
    0.42
    lg
    0.42
    Activations Density 3.542%

    No Known Activations