© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39101
    Prev
    Next
    INDEX
    Explanations

    years, passing time

    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_3_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
     at
    0.91
    ening
    0.90
    ek
    0.87
    ennen
    0.79
    ort
    0.77
    elling
    0.76
    ↵↵
    0.75
    oping
    0.73
    ape
    0.72
    elt
    0.72
    POSITIVE LOGITS
    した
    0.84
     ngũ
    0.80
    ли
    0.77
    ی
    0.75
     với
    0.72
     lịch
    0.70
     tarifas
    0.70
     julho
    0.70
     koniec
    0.69
     settembre
    0.69
    Activations Density 0.000%

    No Known Activations