© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14505
    Prev
    Next
    INDEX
    Explanations

    dates with suffixes, numbers, and separators

    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_13_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
    ння
    0.42
    นี้
    0.38
    ▦
    0.36
    мые
    0.36
    nél
    0.36
    頂き
    0.36
     πι
    0.36
    fler
    0.35
    rà
    0.34
    ératures
    0.34
    POSITIVE LOGITS
    ের
    0.49
    s
    0.44
    ק
    0.41
    0
    0.40
     or
    0.40
     for
    0.40
    ט
    0.39
    ad
    0.39
    _
    0.39
     jean
    0.39
    Activations Density 0.050%

    No Known Activations