© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51363
    Prev
    Next
    INDEX
    Explanations

    dial

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     බො
    0.42
    媇
    0.42
    瓄
    0.41
    㖘
    0.39
     vaid
    0.39
    Hai
    0.39
    Bai
    0.39
    蘼
    0.38
    Khokhlov
    0.38
    Kamol
    0.38
    POSITIVE LOGITS
    UNITED
    0.44
     appropriate
    0.43
     One
    0.39
     UK
    0.39
     Bands
    0.38
     UNITED
    0.37
     geeign
    0.37
     flannel
    0.36
     United
    0.36
    One
    0.36
    Activations Density 0.002%

    No Known Activations