© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33969
    Prev
    Next
    INDEX
    Explanations

    hey guys

    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_3_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
    ן
    0.96
    هاي
    0.81
    ри
    0.77
     reiterate
    0.68
     சொல்க
    0.67
    AN
    0.67
    irii
    0.66
    리
    0.66
    IN
    0.65
     courteous
    0.65
    POSITIVE LOGITS
    。
    0.87
    in
    0.72
    ))
    0.68
    to
    0.62
    D
    0.59
    ب
    0.58
    可以
    0.56
    وم
    0.55
    市
    0.55
    ்கலை
    0.55
    Activations Density 0.000%

    No Known Activations