© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4351
    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_39_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
     factura
    0.44
    𝒋
    0.41
    الحكم
    0.40
     ହ
    0.40
    utat
    0.39
     darn
    0.38
    yuk
    0.38
    한다는
    0.38
    uttered
    0.37
     Karlsson
    0.37
    POSITIVE LOGITS
     office
    0.43
    首席
    0.42
     release
    0.41
     discharge
    0.39
    oral
    0.38
     masts
    0.38
     ties
    0.36
    ασία
    0.36
    Ê
    0.36
     refinement
    0.36
    Activations Density 0.000%

    No Known Activations