© 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. 38952
    Prev
    Next
    INDEX
    Explanations

    verge, vergi, vergä, verb, ver

    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
    ため
    0.73
     confronting
    0.71
    ﻧ
    0.70
     confid
    0.69
    (^^
    0.68
     bluntly
    0.68
    да
    0.68
     descended
    0.68
     championed
    0.68
     разработки
    0.67
    POSITIVE LOGITS
    v
    0.79
    ders
    0.77
    j
    0.76
    et
    0.74
    don
    0.73
    die
    0.71
    T
    0.70
    n
    0.70
    an
    0.69
    d
    0.69
    Activations Density 0.000%

    No Known Activations