© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178381
    Prev
    Next
    INDEX
    Explanations

    what are you doing

    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_29_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
     arguably
    0.44
    odat
    0.39
    放題
    0.38
     **
    0.37
     allegedly
    0.37
    strates
    0.37
    υκ
    0.36
     *
    0.36
     Card
    0.36
     Although
    0.35
    POSITIVE LOGITS
    ິນ
    0.44
     shadowy
    0.41
    ვი
    0.40
     innocuous
    0.40
     expositions
    0.40
    mede
    0.39
     दीन
    0.39
    ⦖
    0.38
    ində
    0.38
    marginY
    0.38
    Activations Density 0.004%

    No Known Activations