© 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. 103385
    Prev
    Next
    INDEX
    Explanations

    suitable or appropriate for

    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
    ו
    1.55
    ي
    1.45
    ва
    1.43
    ா
    1.43
    다
    1.41
    자
    1.39
    ל
    1.22
    ু
    1.21
    ומי
    1.20
    ా
    1.20
    POSITIVE LOGITS
     on
    0.97
     जिसकी
    0.95
     जिसमें
    0.89
     जिसका
    0.89
    ting
    0.87
     which
    0.83
    with
    0.82
     जिसके
    0.82
     with
    0.80
    ley
    0.78
    Activations Density 0.001%

    No Known Activations