© 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. 121943
    Prev
    Next
    INDEX
    Explanations

    jaques, que, jaigarh, Cartier

    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
    i
    1.05
    r
    1.03
    u
    1.02
    im
    0.86
    un
    0.82
    ant
    0.80
    ir
    0.80
    v
    0.79
    S
    0.76
    er
    0.72
    POSITIVE LOGITS
     on
    0.68
    ﻪ
    0.68
     gearbox
    0.64
    д
    0.60
    ш
    0.59
     penyakit
    0.59
    ոն
    0.58
    рсә
    0.58
     as
    0.57
     inducible
    0.55
    Activations Density 0.000%

    No Known Activations