© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18142
    Prev
    Next
    INDEX
    Explanations

    sausage

    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_15_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
    Ⅴ
    0.50
    飭
    0.50
     cig
    0.50
     literat
    0.49
    Categ
    0.48
    inaria
    0.48
     prostit
    0.48
    cig
    0.47
    mvnrepository
    0.47
    촐
    0.47
    POSITIVE LOGITS
    દ
    0.59
     وق
    0.57
    به
    0.53
    anesi
    0.53
    $\
    0.52
    ه
    0.52
    وم
    0.51
    0
    0.51
    ませんが
    0.50
    ה
    0.50
    Activations Density 0.005%

    No Known Activations