© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173977
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     vall
    0.19
     adjacent
    0.19
     /^
    0.19
     spazio
    0.19
    //
    0.19
     aval
    0.19
     espacio
    0.18
     Override
    0.18
     four
    0.18
     તમે
    0.18
    POSITIVE LOGITS
    roth
    0.23
     ซ
    0.22
     feita
    0.22
    र्सन
    0.21
     ደ
    0.21
     に
    0.20
     จ
    0.20
    acelet
    0.20
    ερ
    0.20
     സ്ത്രീ
    0.20
    Activations Density 0.003%

    No Known Activations