© 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. 62242
    Prev
    Next
    INDEX
    Explanations

    clef, clefs

    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
    ill
    1.12
    .
    1.12
    ir
    1.06
    il
    0.97
    )
    0.97
    í
    0.93
     r
    0.89
     మాత్రం
    0.88
     jouw
    0.83
    ungen
    0.82
    POSITIVE LOGITS
    at
    1.45
    و
    1.40
    ับ
    1.36
    在
    1.31
     as
    1.29
    ق
    1.27
    но
    1.19
    த்தில்
    1.17
    า
    1.13
    am
    1.09
    Activations Density 0.000%

    No Known Activations