© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199498
    Prev
    Next
    INDEX
    Explanations

    red and colors

    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_15_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
     circular
    0.19
     д
    0.19
    !
    0.18
     abord
    0.17
     घे
    0.17
     baño
    0.17
     ২০১৯
    0.17
    こちらの
    0.17
    isyon
    0.17
     tinted
    0.17
    POSITIVE LOGITS
    While
    0.22
    Walking
    0.22
    ໋
    0.21
    Insurance
    0.20
     Needless
    0.19
     Vicar
    0.19
    Obviously
    0.19
    hile
    0.19
    When
    0.19
    Jf
    0.19
    Activations Density 0.035%

    No Known Activations