© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    ; followed by command or data

    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
    ي
    3.22
    ्स
    3.08
    不是
    2.75
    зидента
    2.74
    ssä
    2.66
    ные
    2.65
     helic
    2.62
    но
    2.58
    rd
    2.57
    ?>"
    2.57
    POSITIVE LOGITS
    ت
    2.93
    $;
    2.64
    _;
    2.33
     परंतु
    2.32
    под
    2.29
    mais
    2.24
    _,
    2.19
    geq
    2.10
    ào
    2.09
    er
    2.08
    Activations Density 0.084%

    No Known Activations