© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10041
    Prev
    Next
    INDEX
    Explanations

    separators and numbers

    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_13_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
    gm
    0.35
    قیع
    0.34
    。</
    0.34
    gunakan
    0.33
    ⿹
    0.33
    tidak
    0.33
     عمومی
    0.32
    ᒎ
    0.32
    тической
    0.32
    クロマト
    0.32
    POSITIVE LOGITS
     ikon
    0.32
    ader
    0.31
     que
    0.31
    ady
    0.30
     Islander
    0.30
    "
    0.30
     BTC
    0.30
     lok
    0.30
     kle
    0.29
     CBD
    0.29
    Activations Density 0.025%

    No Known Activations