© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7894
    Prev
    Next
    INDEX
    Explanations

    sentences where the speaker is telling someone either what they need to know or what they want to know

    oai_token-act-pair · gemini-2.0-flash

    questions

    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
     help
    -1.88
    help
    -1.55
     Help
    -1.42
    Help
    -1.39
     Hilfe
    -1.33
     aid
    -1.28
     ayuda
    -1.27
     помощи
    -1.25
     HELP
    -1.18
     ajuda
    -1.17
    POSITIVE LOGITS
    IntoConstraints
    0.94
     فريبيس
    0.90
    setVerticalGroup
    0.90
    HomeAsUpEnabled
    0.81
    EDEFAULT
    0.76
     ویکی‌پدیا
    0.74
    BufferException
    0.73
     ModelExpression
    0.72
    InSection
    0.71
    HtmlAttribute
    0.71
    Activations Density 0.613%

    No Known Activations