© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27793
    Prev
    Next
    INDEX
    Explanations

    Benz, whole

    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_40_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
    ʋ
    0.18
    䒿
    0.18
     јо
    0.17
    หว
    0.17
    ﻱ
    0.17
    olius
    0.17
     」,
    0.17
     tə
    0.17
    ious
    0.17
    ETHER
    0.17
    POSITIVE LOGITS
     গণহত্যার
    0.19
    SpringBoot
    0.18
     záp
    0.18
     Perp
    0.18
     Ре
    0.18
    elleen
    0.18
     concili
    0.18
     Part
    0.17
     Macro
    0.17
    首
    0.17
    Activations Density 0.063%

    No Known Activations