© 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. 127467
    Prev
    Next
    INDEX
    Explanations

    date or manager keywords

    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
    ط
    0.77
    드
    0.76
    した
    0.75
    вает
    0.75
    ک
    0.74
    4
    0.73
    ول
    0.73
    ص
    0.72
    いる
    0.71
    tl
    0.70
    POSITIVE LOGITS
     alloy
    0.63
     decoder
    0.63
    o
    0.63
     batch
    0.61
     sauce
    0.61
     orthogonal
    0.61
     doorbell
    0.61
     engine
    0.61
     দুই
    0.60
     biofilm
    0.57
    Activations Density 0.002%

    No Known Activations