© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159617
    Prev
    Next
    INDEX
    Explanations

    kommerziell

    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_2_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
    ال
    1.19
    ان
    1.14
    ag
    1.13
    ת
    1.07
    ки
    1.03
    ı
    1.01
    an
    1.00
    liness
    0.98
     అందు
    0.97
    us
    0.96
    POSITIVE LOGITS
    $
    1.02
     The
    0.95
    )
    0.93
    с
    0.89
    সংখ্যক
    0.82
    сів
    0.79
    ス
    0.78
    ו
    0.77
     poignant
    0.77
    ATED
    0.76
    Activations Density 0.000%

    No Known Activations