© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34041
    Prev
    Next
    INDEX
    Explanations

    is a / is an

    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_31_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
     Ventil
    0.22
    ீக
    0.19
     כש
    0.18
    樎
    0.18
    യാണ്
    0.18
     🤔
    0.18
     सीएम
    0.17
    пису
    0.17
    椽
    0.17
    ǎn
    0.17
    POSITIVE LOGITS
     ح
    0.21
    தால்
    0.19
    Delivery
    0.19
     ನೇ
    0.19
     š
    0.18
    Jur
    0.18
     LSD
    0.18
    一款
    0.18
    Raw
    0.17
    Global
    0.17
    Activations Density 0.098%

    No Known Activations