© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44887
    Prev
    Next
    INDEX
    Explanations

    shine, hold, graces

    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_13_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
    ப்படுத்த
    0.49
    のが
    0.48
     cama
    0.46
    مح
    0.46
    カ
    0.46
     shine
    0.45
    滃
    0.44
     importanti
    0.44
     পাঞ্জ
    0.43
    オン
    0.42
    POSITIVE LOGITS
     Devin
    0.46
     V
    0.45
    .",
    0.40
    .',
    0.40
    ',$
    0.40
     A
    0.39
     Geographic
    0.39
     Josie
    0.39
     Harbor
    0.39
     Zack
    0.39
    Activations Density 0.031%

    No Known Activations