© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203979
    Prev
    Next
    INDEX
    Explanations

    out

    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_46_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
    Mou
    0.42
     Mou
    0.39
     Moll
    0.39
     Shor
    0.39
     Strikes
    0.38
    individuals
    0.38
    or
    0.37
     ?></
    0.37
    Epoch
    0.36
     गे
    0.36
    POSITIVE LOGITS
     law
    0.57
    law
    0.46
     Law
    0.44
    LAW
    0.41
     LAW
    0.40
    ItemBackground
    0.40
    馭
    0.39
    Law
    0.38
     unsub
    0.38
     μεγαλ
    0.37
    Activations Density 0.001%

    No Known Activations