© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15570
    Prev
    Next
    INDEX
    Explanations

    bootstrap framework usage

    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_40_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
    갬
    0.41
    浮か
    0.38
     गोले
    0.38
     workstation
    0.38
     Monique
    0.37
    лини
    0.36
    戰爭
    0.36
    riera
    0.35
     लाइब्रेरी
    0.35
     अन्दर
    0.35
    POSITIVE LOGITS
     horizontal
    0.40
     vertical
    0.39
    짚
    0.39
    カル
    0.38
    ोजना
    0.38
     verticales
    0.38
     híbr
    0.37
    Horizontal
    0.37
     Vertical
    0.37
     হায়
    0.37
    Activations Density 0.001%

    No Known Activations