© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8325
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting

    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
    要
    0.49
    それでは
    0.48
    その
    0.47
    йти
    0.47
    Besides
    0.45
    Ber
    0.44
     anderer
    0.43
    Не
    0.43
    tile
    0.43
        
    0.42
    POSITIVE LOGITS
     boli
    0.63
    ೯
    0.61
    ী
    0.61
     partially
    0.61
     documenting
    0.60
    €”
    0.60
     Respiratory
    0.60
    <unused2091>
    0.60
     Ці
    0.60
     refueling
    0.59
    Activations Density 0.042%

    No Known Activations