© 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. 3181
    Prev
    Next
    INDEX
    Explanations

    well-being

    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
    ++++
    0.68
     '.';
    0.66
     missp
    0.65
     CFU
    0.65
     Magnificent
    0.64
     negar
    0.64
     frm
    0.63
    প্রশ
    0.62
    $('#
    0.62
     commas
    0.62
    POSITIVE LOGITS
    де
    0.83
    і
    0.76
    у
    0.74
     navide
    0.65
     imagined
    0.63
    es
    0.63
    dy
    0.63
     растений
    0.62
     związane
    0.62
    નું
    0.62
    Activations Density 0.018%

    No Known Activations