© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229510
    Prev
    Next
    INDEX
    Explanations

    bb

    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
    玾
    0.46
    Ele
    0.40
     ele
    0.39
     Ele
    0.39
     gimmick
    0.36
    ungere
    0.35
    народ
    0.35
    Recognizer
    0.35
    话
    0.35
    inp
    0.35
    POSITIVE LOGITS
    BB
    0.46
    ẩm
    0.41
    bb
    0.40
     बीबी
    0.39
    ابا
    0.38
     اش
    0.38
     MB
    0.37
     BB
    0.37
     एमसी
    0.37
     DONE
    0.36
    Activations Density 0.000%

    No Known Activations