© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4753
    Prev
    Next
    INDEX
    Explanations

    glass of

    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
    джа
    2.62
    ik
    2.53
    д
    2.47
    یط
    2.39
    или
    2.35
    ㅢ
    2.34
    та
    2.32
    Д
    2.32
    itatea
    2.31
    تل
    2.24
    POSITIVE LOGITS
    राधिक
    3.31
    ˖
    2.69
    }}^{\
    2.42
     maravill
    2.40
    AsyncKeyState
    2.39
     hindsight
    2.37
     soweit
    2.37
     supersymmetry
    2.35
     дочь
    2.34
    harmony
    2.33
    Activations Density 0.031%

    No Known Activations