© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84296
    Prev
    Next
    INDEX
    Explanations

    feng followed by Shen or Lithium

    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_0_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
    -
    2.13
    1.51
     (
    1.45
    -'
    1.16
    EN
    1.11
     affiliation
    1.08
    ishment
    1.07
    /
    1.07
     accommodations
    1.06
    u
    1.05
    POSITIVE LOGITS
    ت
    1.56
    る
    1.48
    1
    1.48
    َ
    1.45
    ın
    1.45
    ب
    1.43
    s
    1.34
    ш
    1.29
    ের
    1.27
    ப்படுகிறது
    1.24
    Activations Density 0.000%

    No Known Activations