© 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. 38115
    Prev
    Next
    INDEX
    Explanations

    model-free / model-based

    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
    मधून
    0.88
    ב
    0.82
    मधील
    0.77
    는
    0.71
    ように
    0.68
    は
    0.67
    ปี
    0.66
    ;
    0.66
    들과
    0.66
    to
    0.65
    POSITIVE LOGITS
    t
    0.71
     infringing
    0.66
     cél
    0.60
    tım
    0.59
    volent
    0.59
     órg
    0.59
     fris
    0.59
     richting
    0.59
     Delphi
    0.58
    curso
    0.58
    Activations Density 0.003%

    No Known Activations