© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212291
    Prev
    Next
    INDEX
    Explanations

    diagonalization Argumen

    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_5_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
    ק
    1.90
    지
    1.81
    ک
    1.43
    ق
    1.38
    تی
    1.38
    ید
    1.31
    きた
    1.29
    ס
    1.27
    으며
    1.25
    ങ്ങൾ
    1.24
    POSITIVE LOGITS
    '
    2.06
    et
    1.60
    at
    1.52
    ing
    1.45
     I
    1.43
    ed
    1.37
    al
    1.31
    AT
    1.30
    \
    1.30
    er
    1.25
    Activations Density 0.000%

    No Known Activations