© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195885
    Prev
    Next
    INDEX
    Explanations

    do the trick

    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_15_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
    f
    0.65
    d
    0.63
    ers
    0.58
    th
    0.57
    ter
    0.54
    ver
    0.54
    rer
    0.54
    r
    0.52
    b
    0.52
    rin
    0.52
    POSITIVE LOGITS
     região
    0.57
    眹
    0.57
     própria
    0.53
     Até
    0.53
     நகரம்
    0.52
     proclaiming
    0.52
    گیرد
    0.52
     sprzedaży
    0.51
     główn
    0.51
     była
    0.49
    Activations Density 0.002%

    No Known Activations