© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194747
    Prev
    Next
    INDEX
    Explanations

    Option, Important, Key

    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_27_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
    を示す
    0.34
    岱
    0.34
    ContentLoaded
    0.33
     التجار
    0.33
    tgt
    0.33
    ilever
    0.32
    ൽപ്പന
    0.32
    reader
    0.32
    储
    0.32
    plectic
    0.32
    POSITIVE LOGITS
     treating
    0.40
     Hana
    0.40
     Tunnel
    0.38
    పోయ
    0.37
     dodge
    0.36
     Treating
    0.36
     ওয়ার্ড
    0.36
    ้ม
    0.36
     reap
    0.36
     Han
    0.35
    Activations Density 0.001%

    No Known Activations