© 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. 46884
    Prev
    Next
    INDEX
    Explanations

    sea captain names and terms

    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
    فك
    0.72
    ו
    0.64
    وون
    0.61
    ומי
    0.61
    ווי
    0.61
    ために
    0.59
     reconocer
    0.58
     высоких
    0.57
    지
    0.57
    usste
    0.56
    POSITIVE LOGITS
    ne
    0.77
    lin
    0.77
    t
    0.75
    dan
    0.72
     in
    0.68
    the
    0.66
    dat
    0.66
    de
    0.65
     Agency
    0.64
    a
    0.63
    Activations Density 0.000%

    No Known Activations