© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35193
    Prev
    Next
    INDEX
    Explanations

    sicher beherrschen

    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
    Совет
    0.35
    ẹ̀
    0.31
    CB
    0.31
    GPS
    0.30
     போதும்
    0.30
    SWITCH
    0.30
    𝖚
    0.30
     sevgili
    0.30
     ለአ
    0.30
    ૪
    0.29
    POSITIVE LOGITS
    的情況
    0.32
    不久
    0.31
     Spa
    0.31
     Recon
    0.31
     spa
    0.31
     Ryd
    0.30
     რო
    0.30
     ribonucle
    0.29
    ड़ी
    0.29
     recognised
    0.29
    Activations Density 0.011%

    No Known Activations