© 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. 39197
    Prev
    Next
    INDEX
    Explanations

    words ending ing

    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
     ہی
    0.42
     горных
    0.39
     Amph
    0.39
    宏
    0.38
     막
    0.36
     δυ
    0.36
     Macro
    0.36
     ही
    0.36
     Agricultura
    0.35
    ",(
    0.34
    POSITIVE LOGITS
    ting
    0.59
    iving
    0.52
    ピング
    0.49
    fting
    0.49
    ving
    0.49
    tting
    0.49
    ping
    0.48
    ティング
    0.47
    팅
    0.46
    aying
    0.45
    Activations Density 0.001%

    No Known Activations