© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211274
    Prev
    Next
    INDEX
    Explanations

    game lore

    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_20_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
     inguinal
    0.35
    瘾
    0.35
    search
    0.34
     searches
    0.34
    opencamera
    0.34
     acompa
    0.34
     ”.
    0.34
    onese
    0.33
    pall
    0.33
     '|')
    0.33
    POSITIVE LOGITS
    pton
    0.38
    寸
    0.37
    дис
    0.36
    ft
    0.35
     লিমি
    0.34
     구간
    0.33
    敬
    0.33
     trat
    0.33
    닷
    0.32
     शास्त्र
    0.32
    Activations Density 0.005%

    No Known Activations