© 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. 41378
    Prev
    Next
    INDEX
    Explanations

    coffee cup

    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
     in
    0.77
    ния
    0.76
    the
    0.73
    ak
    0.70
    ed
    0.69
    il
    0.68
    s
    0.65
    eq
    0.65
    ts
    0.64
    ting
    0.64
    POSITIVE LOGITS
     врача
    0.64
     comedian
    0.63
     Zhi
    0.62
     comedic
    0.61
    കര്‍
    0.60
     novels
    0.59
     Ż
    0.59
     Garuda
    0.58
    ム
    0.58
     proteção
    0.58
    Activations Density 0.014%

    No Known Activations