© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45821
    Prev
    Next
    INDEX
    Explanations

    data management

    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_22_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
    ovec
    0.39
    statistic
    0.36
    度
    0.34
     abhis
    0.34
    不可
    0.33
    닉
    0.32
     akh
    0.32
    amus
    0.32
     سابق
    0.32
     EGF
    0.32
    POSITIVE LOGITS
     managed
    0.37
     dạy
    0.35
     manages
    0.34
    长大
    0.34
     deteriorate
    0.33
    }}$,
    0.33
    Baltimore
    0.33
     Maturity
    0.33
    笃
    0.33
     mediated
    0.33
    Activations Density 0.000%

    No Known Activations