© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139232
    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_37_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
    หัว
    0.41
     beds
    0.40
    neos
    0.39
     परिसर
    0.38
     chiffon
    0.37
     Schw
    0.37
     moan
    0.37
     }^{+}
    0.37
     shaw
    0.37
    鸪
    0.36
    POSITIVE LOGITS
    Picture
    0.39
    Vertical
    0.39
    યુ
    0.39
     জিজ্ঞ
    0.39
    を取得
    0.39
    ARGB
    0.39
    θη
    0.39
     транспорта
    0.38
     flatter
    0.37
     Thiết
    0.37
    Activations Density 0.000%

    No Known Activations