© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3087
    Prev
    Next
    INDEX
    Explanations

    x4 foundations

    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_5_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
    mei
    0.66
     frameN
    0.65
     års
    0.65
     bearded
    0.65
    齬
    0.65
    punctuation
    0.64
     Rxh
    0.63
     seizure
    0.61
     mutilated
    0.61
    笾
    0.61
    POSITIVE LOGITS
    +}$
    0.70
    l
    0.60
    of
    0.59
    能
    0.58
     Voting
    0.57
     যায়
    0.56
     ভাগ্যবান
    0.56
    cknowled
    0.55
    एस
    0.55
    Dé
    0.55
    Activations Density 0.015%

    No Known Activations