© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85408
    Prev
    Next
    INDEX
    Explanations

    specific dates or years

    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_23_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
    想像
    0.44
     اريد
    0.44
    direccion
    0.43
    deprecated
    0.41
     متعلقه
    0.40
     intensa
    0.40
     utilised
    0.39
    ڏ
    0.38
    愀
    0.38
     뒷
    0.37
    POSITIVE LOGITS
     synergies
    0.41
     ಅನು
    0.37
     column
    0.36
    ogi
    0.35
    annulation
    0.34
    களை
    0.34
    arlings
    0.34
     concentration
    0.34
    roughs
    0.34
     House
    0.33
    Activations Density 0.003%

    No Known Activations