© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245029
    Prev
    Next
    INDEX
    Explanations

    act as

    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_40_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
     sejumlah
    0.45
     الصغيرة
    0.40
    પુર
    0.39
     harmful
    0.38
     punches
    0.38
     ಅಪಾಯ
    0.38
     нещо
    0.38
     Ն
    0.37
    撵
    0.37
     ríg
    0.37
    POSITIVE LOGITS
    用法
    0.40
    スター
    0.39
    Deliver
    0.37
    到一个
    0.37
     ഉത്സ
    0.37
    Usage
    0.36
    னில்
    0.36
     Usage
    0.36
    是个
    0.35
     играть
    0.35
    Activations Density 0.004%

    No Known Activations