© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85932
    Prev
    Next
    INDEX
    Explanations

    details undisclosed or confidential

    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_23_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
    旄
    0.42
     Promenade
    0.38
    权重
    0.37
     Tayler
    0.36
    expérience
    0.35
    nings
    0.35
    联盟
    0.35
    钺
    0.35
     Laure
    0.35
    ೖ
    0.35
    POSITIVE LOGITS
    ánicos
    0.45
     omitting
    0.41
     omitted
    0.41
    揊
    0.37
     छैन
    0.37
    📼
    0.37
    䡆
    0.37
     sob
    0.36
     appeared
    0.36
     நடி
    0.35
    Activations Density 0.000%

    No Known Activations