© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121272
    Prev
    Next
    INDEX
    Explanations

    Penhaligon, Miller names

    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_27_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
     विरोधी
    0.23
    ेशनल
    0.22
    Ꮂ
    0.22
    совой
    0.21
    itemconfig
    0.21
    憬
    0.21
    ibul
    0.21
    此刻
    0.21
    θεν
    0.21
    indexBuffer
    0.21
    POSITIVE LOGITS
    romad
    0.24
    ’,
    0.24
     vale
    0.24
    །
    0.24
    ’.
    0.23
     aim
    0.23
     regularity
    0.23
    зах
    0.22
     melting
    0.21
    ’:
    0.21
    Activations Density 0.000%

    No Known Activations