© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37394
    Prev
    Next
    INDEX
    Explanations

    going or class

    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_11_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
    ،
    0.33
     facilitate
    0.32
     allege
    0.31
    氦
    0.30
    generate
    0.30
     generate
    0.30
     certify
    0.29
    とっても
    0.29
    ﺩ
    0.29
    ஞ்ஞான
    0.28
    POSITIVE LOGITS
    o
    0.31
    อย่างไร
    0.28
    usr
    0.28
    of
    0.27
    ส
    0.27
    oj
    0.26
    uras
    0.25
    able
    0.25
    urred
    0.25
    oom
    0.25
    Activations Density 0.007%

    No Known Activations