© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198893
    Prev
    Next
    INDEX
    Explanations

    say land 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_50_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
    لاک
    0.43
    RAN
    0.42
     dashing
    0.39
    scss
    0.38
    ust
    0.37
    濟
    0.37
     passe
    0.35
    ły
    0.35
     शान
    0.35
    arj
    0.35
    POSITIVE LOGITS
     bottom
    2.09
     bottoms
    2.02
     Bottom
    1.98
    Bottom
    1.95
    bottom
    1.88
     BOTTOM
    1.80
    底
    1.63
    BOTTOM
    1.59
    底部
    1.39
     底
    1.34
    Activations Density 0.000%

    No Known Activations