© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14803
    Prev
    Next
    INDEX
    Explanations

    reading frames, files, or returning status

    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_13_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
    洄
    0.63
    Então
    0.56
     plein
    0.53
    im
    0.51
    ्याल
    0.50
    珽
    0.50
     yaşayan
    0.50
    lerdir
    0.49
     දැන්
    0.49
    imise
    0.49
    POSITIVE LOGITS
     हनुमान
    0.51
    v
    0.50
     vocals
    0.48
    ης
    0.48
    デニム
    0.46
     bytes
    0.46
     carbons
    0.46
     indium
    0.46
    '
    0.46
     těch
    0.45
    Activations Density 0.025%

    No Known Activations