© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207050
    Prev
    Next
    INDEX
    Explanations

    pajamas

    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
     चिल्ड्रन
    0.47
     rafting
    0.45
     Зу
    0.41
     bipartisan
    0.41
    <0x95>
    0.41
     až
    0.41
     зна
    0.41
    싣
    0.41
     gou
    0.40
    ystycz
    0.40
    POSITIVE LOGITS
     Structured
    0.43
    getSeconds
    0.43
     svih
    0.42
    ong
    0.42
     pressing
    0.41
     নবী
    0.40
     marvell
    0.40
    Shadow
    0.39
    Structured
    0.39
    Structuring
    0.38
    Activations Density 0.001%

    No Known Activations