© 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. 15104
    Prev
    Next
    INDEX
    Explanations

    a mix of initials, greek letters, and variables like those used in mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    Scientific Research Papers

    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
    lepší
    -0.48
     O
    -0.45
     -
    -0.45
     May
    -0.43
    fxml
    -0.42
    â
    -0.40
    boutin
    -0.40
    ...
    -0.40
     â
    -0.40
     An
    -0.40
    POSITIVE LOGITS
    تقاوى
    0.81
    RectangleBorder
    0.79
    elemField
    0.78
     Theſe
    0.74
    دانشنامهٔ
    0.74
    parsedMessage
    0.73
    typeorm
    0.72
    TestingModule
    0.69
     wireType
    0.69
     myſelf
    0.68
    Activations Density 2.586%

    No Known Activations