© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86039
    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_23_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
     moradores
    0.52
    утбу
    0.48
     lugares
    0.45
     যাইত
    0.45
    侷
    0.44
     decir
    0.44
    ुसार
    0.43
     NSMutable
    0.42
    riott
    0.42
    ‖</
    0.41
    POSITIVE LOGITS
    呪
    0.47
    played
    0.44
    콤
    0.42
    equal
    0.39
    섰
    0.39
     президента
    0.37
    evolution
    0.36
    スキル
    0.36
     справ
    0.36
    слав
    0.35
    Activations Density 0.000%

    No Known Activations