© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259883
    Prev
    Next
    INDEX
    Explanations

    boy playing baseball

    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_10_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
     Gettysburg
    0.36
    ema
    0.35
    b
    0.35
    airplane
    0.35
    em
    0.33
    k
    0.33
    ap
    0.33
     TikTok
    0.32
    ly
    0.32
     
    0.31
    POSITIVE LOGITS
    擴
    0.42
    还可以
    0.41
     andDevice
    0.39
    顽
    0.39
    强烈
    0.38
    连锁
    0.38
    <unused2162>
    0.38
    筫
    0.38
    <unused2032>
    0.38
     vững
    0.37
    Activations Density 0.001%

    No Known Activations