© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194293
    Prev
    Next
    INDEX
    Explanations

    apologies and faults

    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_4_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
    2
    0.52
     exécut
    0.49
    Người
    0.49
    觉
    0.48
     een
    0.48
     prá
    0.47
     lát
    0.47
     única
    0.47
    zp
    0.47
     hierv
    0.47
    POSITIVE LOGITS
     例文帳に追加
    0.60
    ೋಗ್ಯ
    0.55
     boyfriend
    0.51
     コス
    0.51
    Austria
    0.51
     criticised
    0.50
     特許庁
    0.49
    िं
    0.49
    }}]{
    0.49
     kilometre
    0.49
    Activations Density 0.000%

    No Known Activations