© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23822
    Prev
    Next
    INDEX
    Explanations

    values or specifications

    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_56_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
    ၊
    0.43
     وأ
    0.38
     அவ்வ
    0.36
     रहती
    0.36
    出来る
    0.35
     چې
    0.35
     anyway
    0.34
     anyways
    0.34
    َّة
    0.34
     ถ้า
    0.34
    POSITIVE LOGITS
    fre
    0.36
    amos
    0.35
     વખતે
    0.35
    ￳
    0.33
     '.')
    0.33
    ｰ
    0.33
    }^{-},
    0.32
     দৌড়ে
    0.32
     Holland
    0.32
     dhad
    0.31
    Activations Density 0.215%

    No Known Activations