© 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. 14737
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    ת
    0.46
     αρχ
    0.45
     MEX
    0.45
     synapses
    0.45
    小便
    0.44
     thư
    0.44
    스와
    0.43
    刚刚
    0.43
     bilateral
    0.43
    گی
    0.42
    POSITIVE LOGITS
    েক্টর
    0.57
    _
    0.55
     نفسه
    0.54
     Баскетбол
    0.54
    MUS
    0.52
    ոն
    0.51
    ?"
    0.50
    .}
    0.50
     должен
    0.50
     Desember
    0.50
    Activations Density 0.011%

    No Known Activations