© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    five year old

    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
    𝙤
    3.93
    𝙨
    3.78
    𝙞
    3.71
    𝙮
    3.63
    𝙡
    3.55
    𝙝
    3.52
    𝙪
    3.40
    𝙣
    3.36
    𝙩
    3.35
    𝙥
    3.31
    POSITIVE LOGITS
    десят
    3.77
    деся
    3.69
     boroughs
    3.61
    pyrazol
    3.27
     WENO
    3.12
    hmC
    3.11
    Просе
    3.01
    ן
    3.00
    ГУ
    2.93
     centering
    2.92
    Activations Density 0.129%

    No Known Activations