© 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. 9859
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical behaviors or actions, and sometimes scientific research results.

    oai_token-act-pair · gemini-2.0-flash

    simulations and mechanisms

    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
     صوتيه
    -0.69
    出版年
    -0.64
    уза
    -0.60
    LookAnd
    -0.59
     functools
    -0.57
     NSCoder
    -0.57
     propOrder
    -0.57
     Normdatei
    -0.56
     createState
    -0.56
    SpringRunner
    -0.54
    POSITIVE LOGITS
     varier
    0.45
     ostavi
    0.44
    parsedMessage
    0.44
    makeText
    0.42
     stability
    0.40
     reticulum
    0.40
    uksen
    0.39
    rtz
    0.38
     Stability
    0.37
    fastjson
    0.37
    Activations Density 1.354%

    No Known Activations