© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6296
    Prev
    Next
    INDEX
    Explanations

    captions and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    িদ্ধ
    2.34
    𝗻
    2.19
    将
    2.19
    e
    2.11
    в
    2.03
    hrs
    2.02
     ét
    2.00
     creer
    1.98
    हील
    1.97
     nhấn
    1.96
    POSITIVE LOGITS
    𝘬
    2.19
    з
    2.11
     forgo
    1.94
    𝘱
    1.93
     misspelled
    1.85
    𝘫
    1.81
    ியார்
    1.81
     gada
    1.80
    లువ
    1.78
    𝘣
    1.76
    Activations Density 0.140%

    No Known Activations