© 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. 194296
    Prev
    Next
    INDEX
    Explanations

    Babylon

    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
     quidem
    0.32
     iam
    0.32
    }".
    0.31
     работал
    0.31
    暏
    0.31
    последствии
    0.30
    দ্দীন
    0.29
     evolved
    0.29
     erhältlich
    0.29
     Talend
    0.29
    POSITIVE LOGITS
     sloop
    0.35
     دقائق
    0.30
     حساس
    0.29
     நாளை
    0.29
     Winkel
    0.29
     लागणार
    0.28
     棉
    0.28
     নৌকা
    0.27
     zestaw
    0.27
     misalignment
    0.27
    Activations Density 0.001%

    No Known Activations