© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51455
    Prev
    Next
    INDEX
    Explanations

    remove or add

    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
    feeling
    0.38
     MODERN
    0.36
     présenté
    0.34
    <0x0B>
    0.32
    roads
    0.31
    뤽
    0.31
    лении
    0.31
     gevoel
    0.30
    edio
    0.30
    •
    0.30
    POSITIVE LOGITS
    TargetFramework
    0.36
     যাতে
    0.33
    NGC
    0.33
    截
    0.31
     Android
    0.31
     নির্দেশ
    0.31
     hanging
    0.30
     FormData
    0.30
    सन्
    0.30
     targeting
    0.29
    Activations Density 0.000%

    No Known Activations