© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125821
    Prev
    Next
    INDEX
    Explanations

    ** colleges and universities

    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
    darkMode
    0.74
     Са
    0.73
     Бе
    0.70
     enjoined
    0.70
     Запа
    0.70
     Само
    0.68
    벧
    0.68
     Мен
    0.68
    на
    0.68
     Бекер
    0.68
    POSITIVE LOGITS
    is
    1.09
    1
    0.97
    are
    0.75
     It
    0.75
     If
    0.74
    You
    0.73
    em
    0.73
    il
    0.71
    The
    0.71
    I
    0.71
    Activations Density 0.001%

    No Known Activations