© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39155
    Prev
    Next
    INDEX
    Explanations

    Slavic verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    在
    0.89
    am
    0.78
    す
    0.76
    鄰
    0.73
    К
    0.72
    on
    0.70
    ن
    0.70
     einzigen
    0.67
    كي
    0.66
     wenige
    0.66
    POSITIVE LOGITS
    :
    0.75
    OP
    0.74
    EM
    0.71
    ının
    0.71
    OO
    0.69
    hovah
    0.69
    IST
    0.68
     determin
    0.68
    )
    0.68
    WAR
    0.67
    Activations Density 0.003%

    No Known Activations