© 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. 203998
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    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
     કરીને
    0.35
    iderman
    0.31
    áticas
    0.30
    ῎
    0.30
    idescent
    0.29
     pious
    0.29
     devout
    0.28
    uffer
    0.28
     joke
    0.28
    *((
    0.28
    POSITIVE LOGITS
     Tiểu
    0.35
     where
    0.34
     где
    0.34
    预
    0.33
    ฒ
    0.33
     小
    0.32
    ฤษ
    0.32
     খ
    0.32
    ฤ
    0.32
    可以使用
    0.32
    Activations Density 0.009%

    No Known Activations