© 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. 194720
    Prev
    Next
    INDEX
    Explanations

    time of day

    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
    ם
    0.66
    ي
    0.59
    E
    0.56
    ड
    0.54
    కు
    0.53
    D
    0.50
    ్యా
    0.50
    Builder
    0.49
    鹌
    0.49
    מי
    0.49
    POSITIVE LOGITS
     emotional
    0.50
     संक्रमण
    0.44
    rivia
    0.44
    nikova
    0.44
    registro
    0.43
     Ulrich
    0.43
    伲
    0.43
     प्रकोप
    0.43
    ertype
    0.43
     చర్చ
    0.43
    Activations Density 0.001%

    No Known Activations