© 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. 90548
    Prev
    Next
    INDEX
    Explanations

    diuretics, grip, Long, bella, chlorofluorocarbons

    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
     can
    0.90
    ;
    0.87
    و
    0.79
    ).
    0.78
     for
    0.76
    >
    0.75
    ),
    0.74
     to
    0.73
     be
    0.73
    ри
    0.70
    POSITIVE LOGITS
    ت
    0.60
    ’
    0.58
    angk
    0.55
    Sprite
    0.53
    nemidophorus
    0.53
    㑬
    0.53
    ക്ക്
    0.52
    iners
    0.51
    两大
    0.51
    儡
    0.51
    Activations Density 0.000%

    No Known Activations