© 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. 136920
    Prev
    Next
    INDEX
    Explanations

    time and period

    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
    isieren
    0.55
    య
    0.54
     pariy
    0.53
     hora
    0.52
    у
    0.52
     horas
    0.51
     cumprimento
    0.51
     dez
    0.50
    ύτε
    0.50
     posição
    0.50
    POSITIVE LOGITS
    :
    0.71
    €.
    0.63
    ,
    0.61
    পত্র
    0.60
    ד
    0.59
    (
    0.57
    (/
    0.56
     imaginations
    0.56
    と
    0.56
    cció
    0.55
    Activations Density 0.000%

    No Known Activations