© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168024
    Prev
    Next
    INDEX
    Explanations

    Prime

    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_56_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
    ="@+
    0.40
     निशाने
    0.39
    branes
    0.38
     ईमान
    0.38
    earn
    0.38
     shutter
    0.37
    porters
    0.37
    permalink
    0.37
     অমৃত
    0.37
    zok
    0.37
    POSITIVE LOGITS
     (+
    0.52
     (`
    0.52
     sub
    0.49
     (&
    0.47
     суб
    0.46
     Sub
    0.45
    (&
    0.45
    Sub
    0.44
     Programming
    0.44
     series
    0.44
    Activations Density 0.002%

    No Known Activations