© 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. 90896
    Prev
    Next
    INDEX
    Explanations

    Fukuyama, Corporation, Grill, Freiburg

    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
    ن
    0.75
    '
    0.73
    ব
    0.67
    ssä
    0.63
    ם
    0.63
     może
    0.61
    polis
    0.61
    '||
    0.60
    വ
    0.60
    pr
    0.59
    POSITIVE LOGITS
     demandes
    0.66
    ী
    0.65
    ih
    0.64
    ement
    0.64
    ят
    0.64
     оро
    0.64
     orifices
    0.63
    ի
    0.61
    ו
    0.61
    の為
    0.60
    Activations Density 0.001%

    No Known Activations