© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141035
    Prev
    Next
    INDEX
    Explanations

    dawn, daylight, dusk, twilight

    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_12_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
    1
    0.35
    te
    0.32
    us
    0.30
     h
    0.30
     i
    0.29
     characters
    0.29
    att
    0.28
    .
    0.28
    am
    0.28
    um
    0.28
    POSITIVE LOGITS
    🌆
    0.34
    🌇
    0.32
     daylight
    0.32
     Dünya
    0.32
     Nava
    0.32
    녈
    0.31
    뻑
    0.31
     функции
    0.31
     Yıld
    0.31
     ఆర్థిక
    0.30
    Activations Density 0.000%

    No Known Activations