© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57095
    Prev
    Next
    INDEX
    Explanations

    Firstly, followed by a comma

    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_11_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
    '
    0.76
    ayla
    0.64
    Bil
    0.56
    ită
    0.54
    ethe
    0.54
    აგ
    0.53
    av
    0.53
    umbi
    0.52
    owego
    0.51
     وك
    0.51
    POSITIVE LOGITS
     soooo
    0.68
     می‌شوند
    0.67
     are
    0.65
    ی
    0.65
    i
    0.64
     急
    0.63
     urgent
    0.63
    ে
    0.62
    ськ
    0.61
    ので
    0.61
    Activations Density 0.000%

    No Known Activations