© 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. 141611
    Prev
    Next
    INDEX
    Explanations

    Creating ScriptableObjects and references

    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
    Equipment
    0.52
    りは
    0.49
    玧
    0.49
    毌
    0.46
     viên
    0.46
    lii
    0.46
    嬿
    0.46
    下的
    0.46
    дели
    0.45
    Sunflower
    0.44
    POSITIVE LOGITS
     BuildConfig
    0.52
     `>=
    0.50
     jeśli
    0.50
     civilization
    0.48
     современ
    0.48
     NLRP
    0.48
     solvation
    0.46
     Civil
    0.46
     antibodies
    0.46
     CBC
    0.46
    Activations Density 0.006%

    No Known Activations