© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235969
    Prev
    Next
    INDEX
    Explanations

    strong positive descriptions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     outside
    0.44
    רית
    0.44
    Outside
    0.43
    ذية
    0.43
     SPECIAL
    0.42
     Outside
    0.42
    特別
    0.42
    욀
    0.41
    阚
    0.40
    मिति
    0.40
    POSITIVE LOGITS
     לד
    0.38
     제시
    0.37
    akte
    0.36
    ledger
    0.36
    诰
    0.36
     прока
    0.35
    顆
    0.35
     ange
    0.34
     ho
    0.34
     better
    0.33
    Activations Density 0.003%

    No Known Activations