© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62564
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    要
    1.76
    ше
    0.57
     要
    0.55
    ný
    0.54
    要知道
    0.53
    nější
    0.52
    на
    0.46
    nými
    0.45
    ne
    0.45
    igste
    0.44
    POSITIVE LOGITS
    igh
    0.82
    aken
    0.64
    aker
    0.63
    못
    0.59
    IGH
    0.57
    aves
    0.55
    ends
    0.54
    eping
    0.49
    ighi
    0.49
    ighed
    0.46
    Activations Density 0.002%

    No Known Activations