© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199520
    Prev
    Next
    INDEX
    Explanations

    rotors, Arch, Wen

    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_12_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
    4
    0.20
    !
    0.18
    ጨማሪ
    0.17
    Begin
    0.17
     thay
    0.17
    Flam
    0.17
    Incre
    0.16
    ophan
    0.16
     आगमन
    0.16
    Gü
    0.16
    POSITIVE LOGITS
    錘
    0.20
    ＰＥ
    0.20
     oversaw
    0.19
     consiguió
    0.18
    р
    0.18
     recuer
    0.18
     দেখিয়ে
    0.18
     начальник
    0.18
    
    0.18
     Quantitative
    0.17
    Activations Density 0.000%

    No Known Activations