© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85924
    Prev
    Next
    INDEX
    Explanations

    tribal President, census debated, cow slaughter

    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_23_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
     participle
    0.33
    নেই
    0.32
    ссий
    0.31
     પાર્
    0.30
    лон
    0.30
    యర్
    0.30
    тие
    0.30
    冬
    0.30
    إذا
    0.29
    ത്തിയാ
    0.29
    POSITIVE LOGITS
     예측
    0.35
     agrarian
    0.34
    勘
    0.33
     stork
    0.33
    agr
    0.32
    discussed
    0.32
    mapping
    0.31
     favours
    0.31
    predict
    0.31
     meine
    0.31
    Activations Density 0.000%

    No Known Activations