© 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. 83091
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     così
    0.37
     ولم
    0.36
     Huerta
    0.35
    嘛
    0.35
     cosidd
    0.35
     tadi
    0.35
     cinemat
    0.34
     Ones
    0.34
     mancanza
    0.34
    吽
    0.34
    POSITIVE LOGITS
    weekend
    0.40
    selves
    0.39
     shadow
    0.38
    sType
    0.38
     சுற்றுலா
    0.38
    indent
    0.36
    olithic
    0.36
     weekend
    0.36
     pilgrimage
    0.36
     دہشت
    0.36
    Activations Density 0.005%

    No Known Activations