© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90899
    Prev
    Next
    INDEX
    Explanations

    Studio Trigger or Ghibli

    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_11_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
     추출
    0.13
     matters
    0.13
    )【
    0.12
    )(-
    0.12
     부분을
    0.12
     찾아
    0.12
    <0xE3>
    0.11
     사용하는
    0.11
     보다
    0.11
    )】
    0.11
    POSITIVE LOGITS
    RootManager
    0.12
     FirstName
    0.12
     artística
    0.11
     be
    0.11
    芓
    0.11
    <0xA6>
    0.11
     kurze
    0.11
    谐
    0.11
    蕞
    0.11
    abe
    0.11
    Activations Density 0.001%

    No Known Activations