© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124152
    Prev
    Next
    INDEX
    Explanations

    genuine effort, impressed, financial, html, smile

    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_3_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
    t
    0.70
    ный
    0.57
    $
    0.57
    ’.
    0.56
    تر
    0.54
    ards
    0.53
     kommenden
    0.53
    Bottle
    0.52
    ض
    0.52
    ್ಯ
    0.52
    POSITIVE LOGITS
     divulg
    0.74
     eseguire
    0.68
     alimenta
    0.68
    al
    0.64
     ejecutar
    0.62
     corrig
    0.61
     resuelve
    0.61
     aval
    0.61
     Consultado
    0.60
     suggestion
    0.60
    Activations Density 0.003%

    No Known Activations