© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196307
    Prev
    Next
    INDEX
    Explanations

    corona, solar corona, corona render

    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_4_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
    ﻃ
    0.15
    ى
    0.15
    ري
    0.15
    ться
    0.14
    лению
    0.14
     scrutin
    0.14
    í
    0.14
    ੋ
    0.14
    len
    0.13
    ()=>{
    0.13
    POSITIVE LOGITS
    the
    0.25
    EL
    0.20
    지
    0.19
    ן
    0.19
    ER
    0.18
    {\
    0.18
    (
    0.17
    IS
    0.17
    ע
    0.17
    That
    0.17
    Activations Density 0.001%

    No Known Activations