© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    bird, underline, formatting

    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
    म
    2.41
    ம
    2.39
    ح
    2.32
    Cet
    2.25
    Введите
    2.16
    ierzchn
    2.15
    ゙
    2.09
    zata
    2.09
    zkod
    2.05
    ্তে
    2.04
    POSITIVE LOGITS
    southeast
    2.33
    ➺
    2.30
    𝒐
    2.30
     különb
    2.30
    推广
    2.24
    更能
    2.23
    modifier
    2.19
    SQLException
    2.18
    üşt
    2.17
    
    2.13
    Activations Density 0.000%

    No Known Activations