© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14907
    Prev
    Next
    INDEX
    Explanations

    time, years, evolution

    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_40_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
    ,\,
    0.40
    丶
    0.40
    ☜
    0.37
     같
    0.36
    、“
    0.36
    のこ
    0.36
    ,$
    0.35
    ີ້
    0.35
    डॉ
    0.35
     ,\
    0.35
    POSITIVE LOGITS
    urg
    0.35
     rue
    0.34
    事に
    0.34
    まれ
    0.33
    ancen
    0.33
    ッキリ
    0.33
    rVert
    0.33
     statistics
    0.32
     uye
    0.32
    riven
    0.32
    Activations Density 0.077%

    No Known Activations