© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    hexadecimal data and mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    numbers and/or code breaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     set
    -0.43
    φα
    -0.42
     Gef
    -0.42
     internal
    -0.41
     vissza
    -0.41
    </strong>
    -0.41
    liferay
    -0.41
     lit
    -0.40
    वल
    -0.39
     another
    -0.39
    POSITIVE LOGITS
     للمعارف
    1.16
    GEBURTSDATUM
    0.97
    aarrggbb
    0.97
     صوتيه
    0.96
     disambiguazione
    0.96
    MigrationBuilder
    0.92
     дописавши
    0.84
     فريبيس
    0.83
    SharedDtor
    0.83
     protoimpl
    0.82
    Activations Density 1.158%

    No Known Activations