© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236381
    Prev
    Next
    INDEX
    Explanations

    blind

    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_46_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
    KY
    0.44
     ஐ
    0.41
     Mongolian
    0.40
    Potato
    0.38
    ไอ
    0.37
     Potato
    0.36
     Suspension
    0.36
    密切
    0.36
    waitKey
    0.35
    デックス
    0.35
    POSITIVE LOGITS
     blind
    0.49
    blind
    0.46
     Blind
    0.42
    盲
    0.42
     Nieto
    0.39
     gat
    0.39
    හා
    0.38
     SRM
    0.37
    Blind
    0.37
     कोषा
    0.37
    Activations Density 0.000%

    No Known Activations