© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166184
    Prev
    Next
    INDEX
    Explanations

    no way of knowing

    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_31_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
     seseorang
    0.39
     ಯಾವುದ
    0.38
     брен
    0.38
    िका
    0.37
     Pa
    0.36
    ᾧ
    0.36
     ಅದನ್ನು
    0.36
     eks
    0.34
    кола
    0.34
     fresh
    0.34
    POSITIVE LOGITS
     Clarence
    0.39
    stedt
    0.39
     stage
    0.37
    外部リンク
    0.37
     избе
    0.37
    жні
    0.37
    Ծ
    0.36
    inare
    0.35
    ![
    0.35
    を読む
    0.35
    Activations Density 0.003%

    No Known Activations