© 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. 5178
    Prev
    Next
    INDEX
    Explanations

    time, day, AM, PM, night

    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
    권
    0.39
    rezent
    0.37
     webbing
    0.37
    izon
    0.36
     seleccione
    0.36
     glaze
    0.36
     kube
    0.35
    権
    0.35
     माम
    0.35
    kube
    0.34
    POSITIVE LOGITS
     Dy
    0.41
    Jacob
    0.40
    Finite
    0.40
    చ
    0.40
    abolic
    0.39
    Fin
    0.39
     Jacob
    0.39
     night
    0.38
     Night
    0.38
     Vereinig
    0.38
    Activations Density 0.102%

    No Known Activations