© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203412
    Prev
    Next
    INDEX
    Explanations

    how do you know

    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_12_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
    아
    0.62
    arrison
    0.57
    arnia
    0.57
    劃
    0.57
    वत्ता
    0.56
    rsvp
    0.55
    error
    0.54
    ясплат
    0.53
    ambio
    0.53
    았
    0.53
    POSITIVE LOGITS
    in
    0.71
     ánimo
    0.63
     condición
    0.60
     objectif
    0.58
     considér
    0.57
    рд
    0.55
     zas
    0.54
     convain
    0.54
     envers
    0.54
     getBitmap
    0.54
    Activations Density 0.000%

    No Known Activations