© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136298
    Prev
    Next
    INDEX
    Explanations

    me here

    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_37_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
    ानीय
    0.39
    दिव
    0.39
     at
    0.38
     Tg
    0.38
    濁
    0.37
     ONLINE
    0.37
    യ്ക്ക
    0.37
    上线
    0.36
     out
    0.36
     Tencent
    0.36
    POSITIVE LOGITS
     गौरी
    0.39
    祇
    0.38
     deren
    0.36
    ubles
    0.34
     bandana
    0.34
     builders
    0.34
     น่ะ
    0.34
    祗
    0.34
     spong
    0.33
     napkin
    0.33
    Activations Density 0.005%

    No Known Activations