© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217299
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     pieno
    0.42
     />;
    0.41
    під
    0.41
    reb
    0.39
    بيب
    0.38
    rains
    0.38
    counting
    0.37
    必要がある
    0.37
    Perspective
    0.37
    inals
    0.36
    POSITIVE LOGITS
     oov
    0.44
    轩
    0.38
     mechan
    0.38
     soru
    0.38
     handicap
    0.36
     Hoover
    0.36
    ARCH
    0.36
     compress
    0.35
    쭈
    0.35
     lh
    0.35
    Activations Density 0.000%

    No Known Activations