© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89628
    Prev
    Next
    INDEX
    Explanations

    already priced

    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
    屽
    0.43
    籶
    0.37
    ക്കി
    0.35
     पली
    0.35
     расположение
    0.34
    帏
    0.34
    baseURL
    0.34
     অবস্থিত
    0.34
    wala
    0.34
    ほうが
    0.34
    POSITIVE LOGITS
     bounce
    0.38
     “
    0.36
     ultram
    0.36
     ‘
    0.36
    ήμε
    0.36
     unloading
    0.35
     da
    0.35
     फस
    0.35
     proclaimed
    0.34
     feder
    0.34
    Activations Density 0.024%

    No Known Activations