© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2949
    Prev
    Next
    INDEX
    Explanations

    foreign and specific characters

    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
     hauled
    1.98
     lingered
    1.94
     PCIe
    1.76
     unitarity
    1.75
     undercut
    1.72
     smelly
    1.70
    粼
    1.68
    𒌆
    1.66
    近年
    1.65
     elbows
    1.65
    POSITIVE LOGITS
    ن
    1.60
    en
    1.52
     seu
    1.48
    ce
    1.45
    zen
    1.44
    ारी
    1.40
    que
    1.36
    ful
    1.35
     ao
    1.35
    ende
    1.32
    Activations Density 0.001%

    No Known Activations