© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 43502
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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_22_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
    ِب
    0.28
    枋
    0.26
     ತುಂಬಾ
    0.25
     eigenen
    0.25
    တစ်ခု
    0.25
     eko
    0.24
    гӀ
    0.24
     ㄹ
    0.24
     જરૂર
    0.24
    }^{(\
    0.24
    POSITIVE LOGITS
    隐藏
    0.25
     erle
    0.23
     Terms
    0.22
     Core
    0.22
     Rights
    0.22
    я
    0.21
     Unix
    0.21
     Fe
    0.20
     Jews
    0.20
    集团
    0.20
    Activations Density 0.137%

    No Known Activations