© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59935
    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_2_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
    '
    1.00
    ция
    1.00
    ↵↵
    0.91
    henyl
    0.91
    си
    0.90
     irgend
    0.89
    that
    0.86
    1
    0.84
     що
    0.84
    రించ
    0.84
    POSITIVE LOGITS
     as
    1.45
    IN
    1.28
    o
    1.28
    ა
    1.25
     by
    1.23
    as
    1.19
    ת
    1.15
     do
    1.13
    و
    1.09
     d
    1.09
    Activations Density 0.000%

    No Known Activations