© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45509
    Prev
    Next
    INDEX
    Explanations

    PLATINUM

    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_22_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
    杽
    0.23
    ﺭ
    0.23
    accay
    0.22
    <unused88>
    0.22
    ackle
    0.22
    aktadır
    0.22
     الحق
    0.21
    उन्
    0.21
    導數
    0.21
    acağı
    0.21
    POSITIVE LOGITS
     twor
    0.23
     palm
    0.22
     από
    0.21
     vise
    0.21
     Demi
    0.21
     wooden
    0.20
     plum
    0.20
    盒
    0.20
     Philos
    0.19
     \[
    0.19
    Activations Density 0.000%

    No Known Activations