© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44719
    Prev
    Next
    INDEX
    Explanations

    repentance and forgiveness

    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_22_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
     Pons
    0.43
     доста
    0.42
     otev
    0.40
     abierto
    0.40
     Prices
    0.40
     DISABLE
    0.40
    嘢
    0.38
     Arrang
    0.38
    瑯
    0.38
     PRODU
    0.38
    POSITIVE LOGITS
    ifferenti
    0.44
     understatement
    0.41
     grappling
    0.40
    alım
    0.40
    ('.');
    0.39
    uur
    0.39
    reter
    0.39
    itatud
    0.39
    flage
    0.38
    تے
    0.38
    Activations Density 0.001%

    No Known Activations