© 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. 258363
    Prev
    Next
    INDEX
    Explanations

    similar themes or data

    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
    Ar
    0.18
     Sc
    0.18
     ens
    0.17
    Sc
    0.17
    e
    0.17
    vt
    0.16
    ace
    0.15
     responsabil
    0.15
    tem
    0.15
    en
    0.15
    POSITIVE LOGITS
    केट
    0.17
     અંગ
    0.17
    官员
    0.17
    !।
    0.16
    راحة
    0.16
    ləşdir
    0.16
    ‎
    0.16
    鱻
    0.15
     tonight
    0.15
     কেন্দ্র
    0.15
    Activations Density 0.005%

    No Known Activations