© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220310
    Prev
    Next
    INDEX
    Explanations

    errorMessage or error clearing

    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_31_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
     integrable
    0.34
     लिखिए
    0.33
     родился
    0.33
     ArrayAdapter
    0.32
     участка
    0.32
    ************/
    0.31
    卞
    0.31
     chimney
    0.30
    跺
    0.30
     *)&
    0.30
    POSITIVE LOGITS
    PSG
    0.38
     конкурен
    0.37
    iflix
    0.33
     PSG
    0.32
     Cit
    0.31
     Shouldn
    0.31
     noticias
    0.31
    Cit
    0.31
     конку
    0.30
    勉強
    0.30
    Activations Density 0.002%

    No Known Activations