© 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. 44274
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     caloric
    0.29
     متع
    0.27
    ㄾ
    0.26
     htim
    0.26
    Declar
    0.26
     आण
    0.24
     solder
    0.24
     onslaught
    0.24
     daemon
    0.24
     неско
    0.24
    POSITIVE LOGITS
     órganos
    0.32
     fünf
    0.27
     দিনে
    0.26
    È
    0.26
    𐰼
    0.26
    HALF
    0.25
     диагности
    0.25
     тексти
    0.25
     große
    0.25
     vijf
    0.25
    Activations Density 0.005%

    No Known Activations