© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145155
    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_0_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
    I
    1.73
    <0x80>
    1.34
    S
    1.30
     einzigen
    1.23
    Danh
    1.17
    B
    1.14
    H
    1.13
    미
    1.13
    K
    1.10
     allgemeinen
    1.09
    POSITIVE LOGITS
    िंग
    1.68
    ي
    1.68
    ing
    1.67
    ة
    1.63
    of
    1.61
    ა
    1.58
    י
    1.55
    ö
    1.52
    ع
    1.47
    কে
    1.46
    Activations Density 0.000%

    No Known Activations