© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48539
    Prev
    Next
    INDEX
    Explanations

    Dialog content

    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_31_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
     драма
    0.36
    发达
    0.35
    运输
    0.35
    걀
    0.34
    mey
    0.33
    ም።
    0.33
    ="|
    0.33
     <!--<
    0.33
     thoại
    0.32
     डिप्ट
    0.32
    POSITIVE LOGITS
     Meaning
    0.35
     cheap
    0.35
     barefoot
    0.35
     meanings
    0.35
     occasions
    0.34
     emperors
    0.34
     rises
    0.34
     lex
    0.33
     cosy
    0.33
     Pig
    0.33
    Activations Density 0.001%

    No Known Activations