© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197802
    Prev
    Next
    INDEX
    Explanations

    Final Cut Pro

    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_4_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
    r
    0.88
     devolver
    0.77
     prazo
    0.75
     requester
    0.74
     gestione
    0.73
     comunitario
    0.70
     deewana
    0.70
     poziomie
    0.68
     mischiev
    0.67
     scienza
    0.67
    POSITIVE LOGITS
    ä
    0.95
    2
    0.92
    ë
    0.83
    ocks
    0.82
    ës
    0.78
    5
    0.77
    از
    0.76
    ül
    0.75
    ě
    0.70
    6
    0.70
    Activations Density 0.000%

    No Known Activations