© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86951
    Prev
    Next
    INDEX
    Explanations

    here we go

    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_18_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
     It
    0.58
     มัน
    0.51
     acest
    0.50
    憊
    0.49
     Of
    0.48
     Importantly
    0.48
     carbohydrates
    0.47
    It
    0.47
     moyennes
    0.46
    gwood
    0.46
    POSITIVE LOGITS
    epochs
    0.46
    symmetric
    0.46
    لين
    0.44
    onk
    0.42
    рана
    0.42
     Berlín
    0.42
     typology
    0.42
    🗣
    0.41
    اريخ
    0.41
    kimi
    0.41
    Activations Density 0.001%

    No Known Activations