© 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. 137143
    Prev
    Next
    INDEX
    Explanations

    Simon

    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
    琭
    0.37
     títulos
    0.37
     компози
    0.34
     बबलू
    0.33
     রচনা
    0.33
    <0xB3>
    0.33
     titul
    0.33
    汁
    0.33
    帽子
    0.32
    ｋ
    0.32
    POSITIVE LOGITS
    (
    0.45
    able
    0.39
    ade
    0.39
    of
    0.39
    udar
    0.38
    uan
    0.37
    ase
    0.35
    vet
    0.35
    edian
    0.35
    ate
    0.34
    Activations Density 0.001%

    No Known Activations