© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208274
    Prev
    Next
    INDEX
    Explanations

    Jud

    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_56_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
    ূপ
    0.39
    isen
    0.39
    𝒅
    0.37
    beda
    0.36
     Chứng
    0.36
    𝙙
    0.35
    𝗣
    0.34
    ސ
    0.34
    𝓗
    0.33
    azie
    0.33
    POSITIVE LOGITS
     Ment
    0.64
    Ment
    0.64
     ment
    0.63
     ments
    0.49
     mentor
    0.46
    ament
    0.46
     mente
    0.45
    amentul
    0.43
    mentor
    0.43
    ment
    0.42
    Activations Density 0.000%

    No Known Activations