© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43225
    Prev
    Next
    INDEX
    Explanations

    highly in-demand in the next five years

    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_22_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
    ('
    0.13
     withdrawal
    0.12
     !=
    0.11
     sangre
    0.11
     DAG
    0.11
     betyd
    0.11
     такими
    0.11
     신
    0.11
    物品
    0.11
     togg
    0.10
    POSITIVE LOGITS
    ังสือ
    0.13
     hale
    0.12
     चैम्पियन
    0.12
    द्दीन
    0.12
    esley
    0.12
     married
    0.11
    જે
    0.11
    űkö
    0.11
    andeep
    0.11
    documentclass
    0.11
    Activations Density 0.000%

    No Known Activations