© 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. 261909
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    ttemberg
    0.45
     temperatures
    0.40
     Temperaturen
    0.40
     faithfully
    0.39
     wersji
    0.38
    ieur
    0.38
    nemidophorus
    0.38
    팁
    0.37
    UniqueID
    0.36
     неделю
    0.36
    POSITIVE LOGITS
     一
    0.39
     Fuller
    0.39
     EXEMPLARY
    0.38
     ATO
    0.38
     Abol
    0.36
     Proto
    0.36
     ato
    0.36
    TT
    0.35
    éter
    0.35
     Otras
    0.35
    Activations Density 0.001%

    No Known Activations