© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    !important

    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
    整備
    0.41
    antum
    0.39
     HEN
    0.38
    톄
    0.36
    ቱ
    0.36
     हनुमान
    0.36
    型の
    0.36
    䜣
    0.36
     beds
    0.35
     Beds
    0.35
    POSITIVE LOGITS
    peri
    0.38
    spir
    0.38
    gaver
    0.37
    ainak
    0.36
    abile
    0.35
    lanan
    0.35
    gür
    0.35
    elez
    0.34
    sek
    0.34
    íveis
    0.34
    Activations Density 0.001%

    No Known Activations