© 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. 46658
    Prev
    Next
    INDEX
    Explanations

    night or overnight

    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
     داعش
    0.51
    হাম
    0.46
    (
    0.42
    先
    0.42
    イ
    0.40
     dulu
    0.39
    ットフォーム
    0.39
    ’
    0.39
     Roots
    0.39
    льні
    0.38
    POSITIVE LOGITS
    Ⲑ
    0.46
     როგორც
    0.46
     overnight
    0.46
     seab
    0.45
    вр
    0.45
     ев
    0.45
     journée
    0.45
     Overnight
    0.45
     日本製
    0.45
    Wr
    0.44
    Activations Density 0.041%

    No Known Activations