© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101881
    Prev
    Next
    INDEX
    Explanations

    Vercel, Netlify, hosting platforms

    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_14_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
    c
    0.35
    n
    0.33
    s
    0.32
    v
    0.31
    er
    0.31
    is
    0.31
    ast
    0.30
    tailed
    0.30
    all
    0.29
    aste
    0.29
    POSITIVE LOGITS
     часу
    0.37
     ଭ
    0.37
     材質
    0.36
     Ста
    0.35
     率
    0.35
     京都
    0.35
     giorni
    0.34
     Đó
    0.33
     PARK
    0.33
     toolPath
    0.33
    Activations Density 0.005%

    No Known Activations