© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42124
    Prev
    Next
    INDEX
    Explanations

    programming code and styles

    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
     hins
    0.46
    怿
    0.44
    шет
    0.41
     swath
    0.41
     proprietor
    0.41
     shattered
    0.41
     tattooing
    0.40
     личности
    0.40
     reinstatement
    0.40
     purg
    0.40
    POSITIVE LOGITS
    İ
    0.42
    İM
    0.41
    resources
    0.40
    览
    0.38
     vendredi
    0.37
    Friday
    0.37
     pertama
    0.36
    vn
    0.36
    vg
    0.36
     kay
    0.36
    Activations Density 0.001%

    No Known Activations