© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    white followed by noun or description

    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
    ے
    1.60
    ional
    1.47
    ции
    1.43
    at
    1.36
     펼
    1.36
    まあ
    1.31
     ý
    1.28
     Bxd
    1.27
     gasp
    1.25
    なあ
    1.24
    POSITIVE LOGITS
    皙
    1.31
    𝒊
    1.29
    स्पद
    1.26
    얗
    1.22
    ′
    1.19
     frantically
    1.19
    𝒉
    1.18
    handleClick
    1.18
     picket
    1.15
    CURSOR
    1.14
    Activations Density 0.040%

    No Known Activations