© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108480
    Prev
    Next
    INDEX
    Explanations

    psyche

    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
    t
    1.79
    ح
    1.58
    ش
    1.46
    O
    1.45
    on
    1.22
    ف
    1.20
    Y
    1.20
    其他
    1.18
     as
    1.16
    an
    1.13
    POSITIVE LOGITS
    -
    1.56
    ни
    1.31
    ’
    1.20
    ור
    1.18
    :
    1.15
    ва
    1.13
    ية
    1.12
     in
    1.09
    ну
    1.07
    ים
    1.06
    Activations Density 0.000%

    No Known Activations