© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141897
    Prev
    Next
    INDEX
    Explanations

    `loader` and closing braces

    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_12_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
     Fuzzy
    0.19
     secrétaire
    0.18
     de
    0.18
     cadrul
    0.18
    ﻣ
    0.17
     verw
    0.17
    ровала
    0.17
     seigneur
    0.17
     compliance
    0.17
     cuales
    0.17
    POSITIVE LOGITS
    g
    0.21
    ul
    0.21
    t
    0.20
    ir
    0.20
    ist
    0.19
    ust
    0.19
    onics
    0.19
    ulint
    0.19
    utt
    0.19
     现在
    0.19
    Activations Density 0.000%

    No Known Activations