© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6173
    Prev
    Next
    INDEX
    Explanations

    warranties of

    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_39_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
    Vict
    0.30
    icus
    0.28
     ض
    0.28
     Vic
    0.27
    Vic
    0.27
    ையே
    0.26
    resh
    0.26
     अंजाम
    0.26
    Jis
    0.26
    Eventually
    0.25
    POSITIVE LOGITS
     klasy
    0.31
     aritmética
    0.29
    bouw
    0.29
    (\|\
    0.29
     బంగారం
    0.29
    ウンド
    0.28
     inoxyd
    0.28
    وابة
    0.28
    ių
    0.28
    罟
    0.27
    Activations Density 0.000%

    No Known Activations