© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7252
    Prev
    Next
    INDEX
    Explanations

    horizontal lines of underscores

    oai_token-act-pair · gemini-2.0-flash

    non-standard characters or symbols

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

    underscores

    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
    featureID
    -0.88
    AccessorTable
    -0.85
    CloseOperation
    -0.72
    principalTable
    -0.66
    ьаж
    -0.61
     pulumi
    -0.61
    Personensuche
    -0.60
     فريبيس
    -0.59
    oredCriteria
    -0.58
    Hozzáférés
    -0.57
    POSITIVE LOGITS
    schemas
    0.47
    lasma
    0.47
    ėtų
    0.46
    __
    0.45
    %%%%%%%%%%%%
    0.43
    πουργ
    0.42
    LETIN
    0.42
     junta
    0.41
    _${
    0.40
     collected
    0.40
    Activations Density 0.280%

    No Known Activations