© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82723
    Prev
    Next
    INDEX
    Explanations

    graduate

    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_53_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
     मुर
    0.48
    Ras
    0.40
    勂
    0.40
    })}{\
    0.40
     thuật
    0.40
    ptir
    0.38
    Mor
    0.38
    豎
    0.38
    叐
    0.38
    कुर
    0.37
    POSITIVE LOGITS
     grad
    1.90
     Grad
    1.45
    grad
    1.34
     GRAD
    1.32
    Grad
    1.23
     grads
    1.14
     gradation
    1.13
    GRAD
    1.05
     graduated
    1.02
     graduate
    1.02
    Activations Density 0.003%

    No Known Activations