© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39294
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     dev
    0.55
     ze
    0.51
     Ses
    0.47
     ot
    0.47
     де
    0.46
    ゼ
    0.45
     vare
    0.44
    devi
    0.43
     Ze
    0.42
    ఎస్‌
    0.41
    POSITIVE LOGITS
    uit
    0.63
    מונה
    0.54
    UIT
    0.54
     zaz
    0.50
     sex
    0.49
    여
    0.48
     ві
    0.48
    شت
    0.46
    בע
    0.45
     opt
    0.45
    Activations Density 0.004%

    No Known Activations