© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7961
    Prev
    Next
    INDEX
    Explanations

    solar and lunar eclipses

    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_40_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
    ssia
    0.41
    hull
    0.38
     assign
    0.37
    ǎi
    0.36
     hort
    0.36
    鹤
    0.36
    াহি
    0.35
    მი
    0.35
    Ⲧ
    0.35
    пі
    0.35
    POSITIVE LOGITS
     eclipse
    2.28
     Eclipse
    2.16
    Eclipse
    2.08
     eclips
    1.99
    eclipse
    1.92
     eclipsed
    1.71
     ECL
    1.14
    clipse
    1.11
     solar
    1.04
     Solar
    1.04
    Activations Density 0.051%

    No Known Activations