© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120572
    Prev
    Next
    INDEX
    Explanations

    ASAP or now

    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_27_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
    剿
    0.40
    ارڈ
    0.38
     অফ
    0.37
     ভারতীয়
    0.37
    ITTLE
    0.36
     ഇന്ത്യൻ
    0.36
     suppuration
    0.35
    ່
    0.35
     perforated
    0.35
    בוה
    0.35
    POSITIVE LOGITS
     ),
    0.40
     (
    0.38
     нов
    0.38
     --
    0.36
     Study
    0.36
    size
    0.35
    <0xE3>
    0.35
     или
    0.34
     so
    0.33
     выпуск
    0.33
    Activations Density 0.000%

    No Known Activations