© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36373
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs

    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_11_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
    !
    0.48
    ט
    0.46
    त
    0.45
    ह
    0.44
    萍
    0.43
    $
    0.42
    स
    0.42
    นัก
    0.41
    耇
    0.41
    >
    0.41
    POSITIVE LOGITS
     रिश्
    0.42
     krä
    0.41
     dislikes
    0.41
     misog
    0.41
     iss
    0.40
    觎
    0.40
     loses
    0.39
    ckså
    0.39
     Gambling
    0.39
     зар
    0.38
    Activations Density 0.019%

    No Known Activations