© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    floating point numbers

    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
    olées
    0.61
    ﻊ
    0.58
    S
    0.55
    ﻒ
    0.53
    ジャー
    0.52
    inins
    0.50
    Mater
    0.50
    店の
    0.49
    ﻮ
    0.49
    𝑆
    0.48
    POSITIVE LOGITS
     ar
    0.52
     poni
    0.47
    сня
    0.47
     Christian
    0.45
     resizing
    0.45
     Ethereum
    0.45
     numeri
    0.45
     pixels
    0.44
     peraturan
    0.44
     sanded
    0.44
    Activations Density 0.084%

    No Known Activations