© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211228
    Prev
    Next
    INDEX
    Explanations

    grandeur

    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
    U
    1.09
    ارة
    1.07
    أ
    1.06
    ங்கள்
    1.04
    فري
    1.04
    עות
    1.03
    ش
    1.02
    עת
    1.01
    ف
    1.01
    ка
    0.99
    POSITIVE LOGITS
    t
    1.61
    i
    1.60
    in
    1.54
    ก
    1.41
    ،
    1.32
    ।
    1.23
    ia
    1.22
    y
    1.22
     on
    1.20
    ي
    1.18
    Activations Density 0.000%

    No Known Activations