© 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. 245281
    Prev
    Next
    INDEX
    Explanations

    digits in years or dates

    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
    Ukraine
    0.36
     Ukraj
    0.36
     جاي
    0.36
     ভগবান
    0.35
     žele
    0.35
     архе
    0.35
     Ичиго
    0.34
    衷
    0.34
     arche
    0.33
    龊
    0.33
    POSITIVE LOGITS
     push
    0.38
     repro
    0.32
     sting
    0.32
    Push
    0.32
     Push
    0.32
    Dib
    0.31
    preprocess
    0.31
     before
    0.30
    push
    0.30
     Sting
    0.30
    Activations Density 0.002%

    No Known Activations