© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104430
    Prev
    Next
    INDEX
    Explanations

    prime numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    libp
    0.35
    ertype
    0.30
    vik
    0.29
    テゴ
    0.29
    ivado
    0.29
     ラウンド
    0.28
    °)
    0.28
    юн
    0.27
    фектив
    0.27
     iterated
    0.27
    POSITIVE LOGITS
     homosexuality
    0.34
     लैंग्वे
    0.34
     التص
    0.33
     disposiciones
    0.33
    재
    0.32
     د
    0.31
    margins
    0.31
     পার্থক্য
    0.30
     language
    0.30
    মস
    0.30
    Activations Density 0.001%

    No Known Activations