© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210811
    Prev
    Next
    INDEX
    Explanations

    new, repair, arrive, beauty

    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_5_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
    s
    1.66
    y
    1.64
     at
    1.57
    ی
    1.55
     to
    1.50
     et
    1.42
     do
    1.18
     di
    1.14
     is
    1.13
     n
    1.10
    POSITIVE LOGITS
    지
    1.42
    л
    1.39
    ل
    1.20
    рт
    1.19
    ють
    1.16
    ку
    1.13
    كون
    1.13
    ání
    1.11
    áv
    1.10
    ке
    1.09
    Activations Density 0.000%

    No Known Activations