© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38557
    Prev
    Next
    INDEX
    Explanations

    East Germany

    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
    de
    0.85
    1
    0.83
    J
    0.73
    bm
    0.70
    OAc
    0.70
    A
    0.68
    OUR
    0.66
    p
    0.66
    V
    0.66
    K
    0.65
    POSITIVE LOGITS
     LIGO
    0.78
    یش
    0.76
     instituciones
    0.75
     دلیل
    0.71
    льність
    0.70
    ración
    0.70
    től
    0.70
    racción
    0.68
     progreso
    0.68
    かで
    0.67
    Activations Density 0.000%

    No Known Activations