© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    man or woman

    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
    decompose
    0.93
    पंजा
    0.92
    被
    0.91
    檚
    0.89
    в
    0.86
    LO
    0.86
    هم
    0.85
     तुझ
    0.84
    难道
    0.82
    Considering
    0.82
    POSITIVE LOGITS
    od
    0.90
    oe
    0.84
     prib
    0.82
    会在
    0.79
     heur
    0.79
    лександ
    0.79
    ども
    0.78
    ړ
    0.77
     donning
    0.75
    রা
    0.75
    Activations Density 0.000%

    No Known Activations