© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2963
    Prev
    Next
    INDEX
    Explanations

    Captain America, Captain Phasma

    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_40_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
     symplect
    0.41
    Maze
    0.40
     کوډ
    0.38
    REACT
    0.38
    Stub
    0.38
    傚
    0.38
    Run
    0.37
    Whatsapp
    0.37
    ᴊ
    0.37
    主人
    0.36
    POSITIVE LOGITS
    谌
    0.44
    nan
    0.40
     translation
    0.38
     eric
    0.38
     traduire
    0.37
    translation
    0.35
    Translation
    0.35
     मुस्लिम
    0.35
     chris
    0.35
     nan
    0.34
    Activations Density 0.043%

    No Known Activations