© 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. 156808
    Prev
    Next
    INDEX
    Explanations

    Tchaikovsky

    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
    ли
    1.24
    ל
    1.10
    นิด
    1.09
    の後
    1.04
    м
    1.02
    ת
    0.97
    х
    0.95
    is
    0.92
    ل
    0.90
    นี่
    0.89
    POSITIVE LOGITS
    EN
    1.26
    ED
    1.20
    ov
    1.13
    \}\
    1.12
    -
    1.11
    ut
    1.06
    EAR
    1.02
    AN
    1.02
    AR
    1.01
    ö
    0.99
    Activations Density 0.000%

    No Known Activations