© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215287
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    令牌
    0.41
    }&
    0.39
     practiced
    0.39
     bookmark
    0.38
     குறு
    0.38
     Balashov
    0.37
     गर
    0.36
     awake
    0.36
     kj
    0.36
    ড়ানো
    0.36
    POSITIVE LOGITS
    нтип
    0.43
    ᙱ
    0.42
    MenuGroup
    0.40
    Terminal
    0.39
    ThreadGroup
    0.39
    ಂತ್
    0.39
    ᖕ
    0.39
     pelea
    0.38
    ূনতম
    0.38
    𒈬
    0.37
    Activations Density 0.000%

    No Known Activations