© 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. 108381
    Prev
    Next
    INDEX
    Explanations

    lick followed by my, dew, or shades

    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
    ну
    1.20
    ua
    1.20
    ud
    1.15
    that
    1.15
    ม
    1.15
    1.09
    ла
    1.08
    อง
    1.03
    ing
    0.99
    ning
    0.98
    POSITIVE LOGITS
    ),
    1.63
    ه
    1.63
    P
    1.38
    س
    1.33
    H
    1.31
    R
    1.30
    K
    1.30
    O
    1.27
    很
    1.27
    F
    1.25
    Activations Density 0.000%

    No Known Activations