© 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. 52579
    Prev
    Next
    INDEX
    Explanations

    family and support

    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
     يتعلق
    0.33
     frequented
    0.32
    ორცი
    0.32
    少年
    0.32
     جمعیت
    0.32
    EOUS
    0.32
     मोर
    0.31
    젠
    0.31
     సామ
    0.31
    ovost
    0.30
    POSITIVE LOGITS
    Support
    0.48
     Support
    0.47
    Supports
    0.47
     Supports
    0.46
     поддержки
    0.43
     supports
    0.43
    supports
    0.43
     support
    0.43
     supportive
    0.43
     apoyo
    0.42
    Activations Density 0.001%

    No Known Activations