© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57558
    Prev
    Next
    INDEX
    Explanations

    The number 4

    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
    Negative Logits
     IDE
    0.49
     Since
    0.44
     This
    0.44
     underlining
    0.44
     *****
    0.42
    This
    0.42
     HE
    0.40
     ~~
    0.39
    Cette
    0.39
     ####
    0.39
    POSITIVE LOGITS
    ruar
    0.41
    plectic
    0.40
    ẓ
    0.38
    istet
    0.38
    optimize
    0.37
    argmin
    0.37
    PatientR
    0.36
     expresar
    0.35
    ₂(
    0.35
    rů
    0.34
    Activations Density 0.005%

    No Known Activations