© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139862
    Prev
    Next
    INDEX
    Explanations

    take

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Lead
    0.96
    Lead
    0.91
     lead
    0.91
    lead
    0.77
     Leads
    0.73
     leads
    0.67
     लीड
    0.66
    铅
    0.64
    leads
    0.61
    鉛
    0.61
    POSITIVE LOGITS
    take
    0.40
    ulka
    0.38
     take
    0.38
    Take
    0.37
    ͇
    0.37
    コス
    0.36
     ऐड
    0.35
     কৌ
    0.35
    ぎ
    0.35
     Take
    0.35
    Activations Density 0.001%

    No Known Activations