© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4815
    Prev
    Next
    INDEX
    Explanations

    output file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apre
    2.25
    නි
    1.72
     Ignore
    1.72
    enance
    1.70
     anharmonic
    1.69
    нии
    1.65
     obvious
    1.64
    ^{-}$
    1.64
     roomId
    1.62
     espe
    1.60
    POSITIVE LOGITS
     donn
    2.02
    teile
    1.94
     wrenches
    1.87
    INION
    1.84
    вшись
    1.70
    $).
    1.70
     besteht
    1.69
     ओपी
    1.69
    inados
    1.66
    يكم
    1.65
    Activations Density 0.061%

    No Known Activations