© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209955
    Prev
    Next
    INDEX
    Explanations

    bluebell, primrose

    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_10_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
     be
    0.91
    R
    0.85
     Informationen
    0.82
     I
    0.80
     Angaben
    0.80
             
    0.80
    //
    0.79
    W
    0.77
     Datos
    0.72
    كتب
    0.70
    POSITIVE LOGITS
    ﻢ
    0.75
    ені
    0.73
    anga
    0.71
     adiabatic
    0.71
     regeneration
    0.69
     deterioration
    0.69
    umping
    0.68
    که
    0.68
    aken
    0.68
    ningarna
    0.68
    Activations Density 0.000%

    No Known Activations