© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59130
    Prev
    Next
    INDEX
    Explanations

    via rail, ferrata, system settings, viavi

    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_11_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
     BRO
    0.54
     Iowa
    0.52
     RR
    0.52
     С
    0.50
     López
    0.50
     Rostock
    0.50
     RID
    0.50
    Issledovatel
    0.50
     Agri
    0.50
    阵容
    0.49
    POSITIVE LOGITS
    ाम्
    0.60
    satisf
    0.52
    optimization
    0.52
    o
    0.51
    ли
    0.50
    atisf
    0.50
    satisfied
    0.50
    restaurant
    0.49
    flavor
    0.49
    balanced
    0.48
    Activations Density 0.000%

    No Known Activations