© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162793
    Prev
    Next
    INDEX
    Explanations

    molecules and imperfections

    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_31_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
    㑯
    0.34
     registered
    0.31
     зарегистри
    0.31
     autorisation
    0.31
     Registered
    0.30
    감을
    0.30
     step
    0.30
    鏻
    0.30
    registered
    0.30
     ದಾ
    0.29
    POSITIVE LOGITS
    மிழ்
    0.27
    reys
    0.26
     fär
    0.26
    americanos
    0.26
     Error
    0.25
    Heavy
    0.25
    긱
    0.25
    ikova
    0.25
    ahiya
    0.25
    iei
    0.25
    Activations Density 0.003%

    No Known Activations