© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88359
    Prev
    Next
    INDEX
    Explanations

    code structure definition

    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_23_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
     потре
    0.38
     FIS
    0.38
     الجام
    0.37
     jednot
    0.37
     rych
    0.36
     затем
    0.36
    ція
    0.36
    ᔾ
    0.36
    緯
    0.35
    녓
    0.35
    POSITIVE LOGITS
    bica
    0.43
    可以直接
    0.42
    tem
    0.41
    arn
    0.38
    sohn
    0.38
    directly
    0.37
    itoare
    0.37
    Keller
    0.36
    nem
    0.36
    accompl
    0.36
    Activations Density 0.010%

    No Known Activations