© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175376
    Prev
    Next
    INDEX
    Explanations

    time** 10:56 PM, 21:46, 11:33pm, 9:00am, 21:15:32, 10:17 PM, 21:06:55.473732

    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_24_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
    怕
    0.43
    ڤ
    0.43
     ძალიან
    0.42
    爣
    0.40
    僳
    0.39
     boredom
    0.38
    cuando
    0.38
    сик
    0.37
    ници
    0.37
    सव
    0.37
    POSITIVE LOGITS
     تاز
    0.38
     Tongue
    0.38
     Poor
    0.35
     u
    0.35
     Pro
    0.34
     dex
    0.34
    ステ
    0.34
    >\
    0.34
    最新
    0.34
    átu
    0.33
    Activations Density 0.000%

    No Known Activations