© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 140071
    Prev
    Next
    INDEX
    Explanations

    high

    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
    ilium
    0.43
     Cu
    0.39
    Cu
    0.38
     ইংরা
    0.38
     সার্বভৌম
    0.36
     hac
    0.36
     hyperlocal
    0.36
     天
    0.35
     regal
    0.34
     orifices
    0.34
    POSITIVE LOGITS
     high
    1.74
    high
    1.70
    High
    1.62
     High
    1.57
    高
    1.38
    HIGH
    1.38
     हाई
    1.36
     عالية
    1.22
     HIGH
    1.19
     उच्च
    1.12
    Activations Density 0.000%

    No Known Activations