© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10637
    Prev
    Next
    INDEX
    Explanations

    mentions of mistakes and errors

    oai_token-act-pair · gemini-2.0-flash

    actions related to stealth or sneaking

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

    sneaking, slipping

    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
    tonode
    -0.66
    elemField
    -0.63
    PreferredItem
    -0.61
    (;;)
    -0.56
    psa
    -0.56
     nakalista
    -0.55
    maus
    -0.54
     Revere
    -0.53
    тли
    -0.53
    setVertical
    -0.52
    POSITIVE LOGITS
     sneak
    1.23
     sneaking
    1.23
     slip
    1.10
     sne
    1.07
     slipped
    1.06
     slipping
    1.02
     creeping
    0.99
    sneak
    0.98
     sn
    0.97
     slips
    0.96
    Activations Density 2.882%

    No Known Activations