© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46199
    Prev
    Next
    INDEX
    Explanations

    low to high indicators

    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_3_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
     shilling
    0.67
    スマートフォン
    0.65
    т
    0.65
    "
    0.65
     cents
    0.64
     diligently
    0.63
     shillings
    0.62
    ೂರ್ಯ
    0.62
    ל
    0.62
     aches
    0.62
    POSITIVE LOGITS
     I
    0.70
    iin
    0.64
     Figma
    0.59
    يًا
    0.59
    জন্য
    0.57
    el
    0.57
    ки
    0.57
     Lesen
    0.56
    iende
    0.55
    าว
    0.55
    Activations Density 0.005%

    No Known Activations