© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50569
    Prev
    Next
    INDEX
    Explanations

    next steps

    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_55_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
    只限平日
    0.43
    ⌯
    0.38
    テゴ
    0.38
     Driven
    0.38
    bindParam
    0.37
     Вайлдберриз
    0.35
    activity
    0.35
     anunciou
    0.35
     Organized
    0.35
    楖
    0.35
    POSITIVE LOGITS
     kä
    0.46
     ಮ
    0.44
     elementi
    0.44
     Indices
    0.44
    制
    0.43
     considérer
    0.43
     elemen
    0.42
     घटने
    0.42
     तत्व
    0.41
     i
    0.41
    Activations Density 0.000%

    No Known Activations