© 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. 14139
    Prev
    Next
    INDEX
    Explanations

    /

    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
     bril
    0.19
     periode
    0.19
     plantings
    0.19
    ᱪ
    0.19
     decap
    0.19
    闥
    0.19
     sphinx
    0.18
     attire
    0.18
     shading
    0.18
     comand
    0.18
    POSITIVE LOGITS
    //
    0.20
    मु
    0.17
    üle
    0.17
    /
    0.17
    报错
    0.17
    最近
    0.16
    KeyDown
    0.16
    سم
    0.16
    Pressure
    0.16
    raccoon
    0.16
    Activations Density 0.001%

    No Known Activations