© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1647
    Prev
    Next
    INDEX
    Explanations

    complicated formatting and probably table entries with mostly whitespace

    oai_token-act-pair · gemini-2.0-flash

    forward slash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    metz
    -0.59
     incontr
    -0.50
    idum
    -0.48
     MATCH
    -0.47
    ghe
    -0.47
     its
    -0.46
    deburg
    -0.46
     ever
    -0.45
     meet
    -0.45
    ifts
    -0.44
    POSITIVE LOGITS
     ControllerBase
    0.77
    principalColumn
    0.74
    الحياه
    0.66
     BoxDecoration
    0.65
    HtmlAttribute
    0.65
     sonora
    0.63
    !*\
    0.62
    ariConfig
    0.62
    öglichkeiten
    0.61
     légales
    0.61
    Activations Density 3.123%

    No Known Activations