© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129499
    Prev
    Next
    INDEX
    Explanations

    KUKA, Kavinsky, Milankovitch

    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_1_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
     of
    1.60
     I
    1.20
     powied
    1.13
    л
    1.09
     with
    1.09
    ل
    1.08
    ፍተኛ
    1.02
    大
    0.98
    ون
    0.98
    ۳
    0.97
    POSITIVE LOGITS
    ו
    1.50
    ↵↵
    1.40
    ↵
    1.31
    ла
    1.28
    าย
    1.23
    ),
    1.19
    '
    1.17
    म
    1.17
    ER
    1.10
    ம்
    1.09
    Activations Density 0.000%

    No Known Activations