© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151071
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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_60_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
    ায়ক
    0.35
     系
    0.34
     afuera
    0.33
     måle
    0.32
     surge
    0.31
     linger
    0.31
    correlation
    0.31
    }}\\
    0.31
    allocate
    0.31
     surg
    0.30
    POSITIVE LOGITS
     z
    2.56
     з
    2.09
     із
    1.74
     ز
    1.68
     aus
    1.52
     из
    1.45
     ז
    1.34
     uit
    1.20
     iz
    1.17
    ｚ
    0.96
    Activations Density 0.030%

    No Known Activations