© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195739
    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_27_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
     pointwise
    0.40
     responsible
    0.40
     heterogeneous
    0.40
     gestational
    0.39
     విషయం
    0.39
    襲
    0.39
     integration
    0.39
     detectable
    0.39
     Montag
    0.39
     obicei
    0.39
    POSITIVE LOGITS
    न्दु
    0.38
    Га
    0.36
    벗
    0.36
    Ри
    0.36
    substring
    0.35
    开发者
    0.35
    На
    0.34
    language
    0.34
    Чем
    0.34
    Ма
    0.33
    Activations Density 0.000%

    No Known Activations