© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110489
    Prev
    Next
    INDEX
    Explanations

    Le Marais

    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
    0
    0.91
    is
    0.89
    are
    0.88
    il
    0.88
    t
    0.87
    ре
    0.71
    ak
    0.68
    c
    0.68
    ᧐
    0.67
    <0x80>
    0.66
    POSITIVE LOGITS
    arnya
    0.88
    是
    0.82
    的
    0.80
    는
    0.75
     μεγάλη
    0.73
    اء
    0.72
    ας
    0.70
    A
    0.68
    zeitig
    0.67
    𝟐
    0.67
    Activations Density 0.005%

    No Known Activations