© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208147
    Prev
    Next
    INDEX
    Explanations

    of the

    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_25_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
     बिज
    0.37
    ရှ
    0.36
    TextBoxColumn
    0.36
    বিজ
    0.35
     procl
    0.35
    숄
    0.35
    ThoughtData
    0.34
     سرکاری
    0.34
    𠄌
    0.34
     tripled
    0.34
    POSITIVE LOGITS
     katika
    0.56
     pada
    0.51
    pada
    0.49
     فى
    0.49
    ｘ
    0.48
    能在
    0.46
     trên
    0.46
    ser
    0.46
    æ
    0.45
     tại
    0.45
    Activations Density 0.006%

    No Known Activations