© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8213
    Prev
    Next
    INDEX
    Explanations

    by other agency

    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
    osim
    0.34
    olim
    0.32
    허
    0.30
     locally
    0.29
     وول
    0.29
    当地
    0.29
     JP
    0.29
     운영
    0.29
    unca
    0.29
    ivir
    0.28
    POSITIVE LOGITS
    દાવાદ
    0.33
    Rr
    0.31
    ಂತ
    0.31
    IMENTO
    0.30
    桉
    0.30
     assent
    0.30
     promot
    0.29
    कों
    0.29
     Rajasthan
    0.29
     adjectives
    0.29
    Activations Density 0.005%

    No Known Activations