© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61840
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     mg
    0.64
     gs
    0.60
     gw
    0.59
     _$
    0.59
     mw
    0.57
     lg
    0.54
     md
    0.53
     mh
    0.53
     mts
    0.53
     adc
    0.52
    POSITIVE LOGITS
    C
    0.60
    U
    0.60
    s
    0.54
    a
    0.54
    M
    0.54
    R
    0.54
    c
    0.53
    r
    0.52
    H
    0.52
    D
    0.51
    Activations Density 0.009%

    No Known Activations