© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215992
    Prev
    Next
    INDEX
    Explanations

    vaping

    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
     buds
    0.40
    ଉ
    0.40
    플레이
    0.40
    プレイヤー
    0.39
     সিগারে
    0.39
     Motorola
    0.39
     शॉ
    0.39
    fault
    0.37
     Fault
    0.37
    خر
    0.37
    POSITIVE LOGITS
    __()
    0.40
     மட
    0.38
    琼
    0.37
    ͉
    0.36
    __[
    0.36
    ობას
    0.35
     incapacity
    0.35
     проце
    0.35
    ⏜
    0.35
    ъ
    0.33
    Activations Density 0.002%

    No Known Activations