© 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. 91241
    Prev
    Next
    INDEX
    Explanations

    all of you

    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
    h
    0.97
    n
    0.91
    ad
    0.86
    ရာ
    0.85
    น
    0.84
    의
    0.84
    ુ
    0.82
    ur
    0.82
    am
    0.82
    ug
    0.82
    POSITIVE LOGITS
     jeweil
    0.75
     colp
    0.75
     problém
    0.71
     litros
    0.68
    tait
    0.68
     механиз
    0.68
     индек
    0.66
     большим
    0.65
    ك
    0.65
     terapi
    0.64
    Activations Density 0.001%

    No Known Activations