© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6167
    Prev
    Next
    INDEX
    Explanations

    the discussion of children making poor choices and attempting to conceal them

    oai_token-act-pair · gemini-2.0-flash

    Errors of judgement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     >=",
    -0.77
    DataAnnotations
    -0.77
     Italijani
    -0.70
     ProtoMessage
    -0.65
     متعلقه
    -0.62
     ExecuteAsync
    -0.61
    లాలు
    -0.57
    HasColumnName
    -0.56
     simplifié
    -0.56
     生命周期
    -0.54
    POSITIVE LOGITS
     mistakes
    0.76
     unwise
    0.68
     imprud
    0.67
     blunder
    0.66
     mistake
    0.66
     decisions
    0.62
     foolish
    0.60
     fool
    0.60
     error
    0.59
     decision
    0.58
    Activations Density 1.588%

    No Known Activations