© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165056
    Prev
    Next
    INDEX
    Explanations

    vehicles

    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_31_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
    컴
    0.32
     ኮ
    0.30
     waarop
    0.30
    hee
    0.29
     infusions
    0.29
     viy
    0.29
     위
    0.29
    cartes
    0.29
     sequ
    0.28
     herm
    0.28
    POSITIVE LOGITS
     Evangelical
    0.35
    🥦
    0.35
    🥒
    0.33
     evangelical
    0.33
     zunehm
    0.33
    🥬
    0.33
    朩
    0.33
    ﻫ
    0.32
    ició
    0.32
    ിക്കാ
    0.32
    Activations Density 0.000%

    No Known Activations