© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195710
    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_4_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
    buatan
    0.59
     résist
    0.53
     refuted
    0.52
     absorbs
    0.52
     membangun
    0.52
    𝘆
    0.52
    transferases
    0.51
     aching
    0.51
     отсутствие
    0.50
     prejudicial
    0.50
    POSITIVE LOGITS
     Lakeside
    0.52
     Floating
    0.48
     Hospice
    0.46
    t
    0.46
     Cascade
    0.45
    Q
    0.45
     tob
    0.44
     collage
    0.43
     Coastal
    0.43
     Ry
    0.43
    Activations Density 0.000%

    No Known Activations