© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90661
    Prev
    Next
    INDEX
    Explanations

    quotes followed by common sentence starters

    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_11_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
     be
    0.28
     the
    0.28
     an
    0.26
     Chloe
    0.25
     a
    0.25
     KPI
    0.25
     el
    0.25
     Cove
    0.24
     pror
    0.24
     ž
    0.24
    POSITIVE LOGITS
     ಸೂಚ
    0.30
    ون
    0.30
    ів
    0.29
    écies
    0.27
    OF
    0.26
    ьогодні
    0.26
     Strengthening
    0.25
    ٹس
    0.25
    ίσ
    0.25
     вигляді
    0.25
    Activations Density 0.011%

    No Known Activations