© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 161981
    Prev
    Next
    INDEX
    Explanations

    data source information

    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
    㳖
    0.40
     legislator
    0.39
    tempHeader
    0.39
    angkah
    0.38
    uento
    0.38
    和田
    0.37
    cieron
    0.37
    㯎
    0.36
    掖
    0.35
    ウッド
    0.34
    POSITIVE LOGITS
     proportionate
    0.39
     proportional
    0.37
    immune
    0.35
    पति
    0.34
     CIN
    0.34
     facial
    0.34
     displays
    0.34
     exhibits
    0.33
     equilibria
    0.33
     cumulative
    0.32
    Activations Density 0.001%

    No Known Activations