© 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. 7304
    Prev
    Next
    INDEX
    Explanations

    opalescent scales

    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
    辕
    0.85
    age
    0.78
    й
    0.75
     prise
    0.72
    iin
    0.71
    轅
    0.68
     premise
    0.67
     лет
    0.67
    я
    0.67
    asının
    0.67
    POSITIVE LOGITS
    naires
    0.80
    ſelf
    0.74
    гласно
    0.73
    urez
    0.70
    есть
    0.67
    ष्ठा
    0.66
    琍
    0.66
     outdated
    0.65
    ுகிறது
    0.64
    ure
    0.62
    Activations Density 0.003%

    No Known Activations