© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108704
    Prev
    Next
    INDEX
    Explanations

    mlb or mlc

    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_1_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
    e
    1.38
    ة
    1.32
    o
    1.23
    ت
    1.23
    ת
    1.22
    т
    1.21
    ა
    1.16
    н
    1.16
    ي
    1.16
    ات
    1.09
    POSITIVE LOGITS
    O
    1.22
     is
    1.07
     year
    1.00
    cm
    0.91
    },
    0.91
    mm
    0.85
    อังกฤษ
    0.84
    cn
    0.84
     a
    0.83
     eraser
    0.82
    Activations Density 0.000%

    No Known Activations