© 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. 257694
    Prev
    Next
    INDEX
    Explanations

    exhale for

    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
    ናል
    0.45
     enshrined
    0.44
    qat
    0.42
     enshr
    0.42
    ᓯ
    0.39
    шек
    0.39
    
    0.39
    Ꮸ
    0.38
     évén
    0.38
     flashed
    0.38
    POSITIVE LOGITS
     container
    0.45
     Korea
    0.42
     Hungarian
    0.41
     Jan
    0.39
     Pasta
    0.38
    Container
    0.38
     ​​
    0.38
     Feb
    0.38
    嘮
    0.38
     Container
    0.38
    Activations Density 0.004%

    No Known Activations