© 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. 7356
    Prev
    Next
    INDEX
    Explanations

    Maldives, MVP

    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
    ка
    2.88
    ST
    2.70
     lapply
    2.45
    ت
    2.43
    ريكي
    2.39
    TA
    2.32
    ே
    2.31
    joke
    2.31
    та
    2.29
    ce
    2.22
    POSITIVE LOGITS
    ../../
    2.91
    ../../../
    2.86
     thio
    2.48
    ſe
    2.37
    ignment
    2.36
     thưởng
    2.23
    }'],
    2.23
     presiding
    2.23
     불구하고
    2.22
     واله
    2.19
    Activations Density 0.022%

    No Known Activations