© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1685
    Prev
    Next
    INDEX
    Explanations

    Morning 9:00 AM

    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_39_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
     dawn
    1.25
     sunrise
    1.13
     ভোর
    1.03
    dawn
    1.02
    Dawn
    0.96
     새벽
    0.95
    朝
    0.94
    sunrise
    0.93
     Dawn
    0.92
     Sunrise
    0.92
    POSITIVE LOGITS
     Nine
    0.40
     Ninth
    0.40
    eight
    0.40
     Eight
    0.39
     九
    0.39
    သမ
    0.38
     八
    0.38
     సంఘ
    0.38
    nine
    0.37
    Nine
    0.37
    Activations Density 0.057%

    No Known Activations