© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134883
    Prev
    Next
    INDEX
    Explanations

    splitting text

    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_37_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
     @"
    0.37
    日常生活
    0.37
     극
    0.35
     cul
    0.35
    ')])
    0.35
     ಎರ
    0.35
    الحمد
    0.34
     Minggu
    0.34
    蒉
    0.34
     believing
    0.34
    POSITIVE LOGITS
     decomposition
    0.78
    decomposition
    0.73
     decompositions
    0.72
     Decomposition
    0.68
     decompose
    0.66
    分解
    0.65
     decomposes
    0.58
     decomposed
    0.57
     decomposing
    0.57
     decom
    0.56
    Activations Density 0.001%

    No Known Activations