© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242274
    Prev
    Next
    INDEX
    Explanations

    numbers and "points"

    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
     Noon
    0.67
     noon
    0.65
    十二
    0.59
    noon
    0.51
     Twelve
    0.48
     午
    0.47
    Twelve
    0.46
     twelve
    0.46
     midday
    0.45
    午
    0.45
    POSITIVE LOGITS
     morning
    0.80
    morning
    0.75
    Morning
    0.75
     Morning
    0.71
     mornings
    0.69
     sabah
    0.63
    朝
    0.63
    9
    0.62
    ９
    0.60
     सुबह
    0.59
    Activations Density 0.019%

    No Known Activations