Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9321
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_31_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
    ങ്ങളെ
    0.79
     Nucle
    0.74
    チェ
    0.72
     يمكن
    0.71
     ممكن
    0.70
     Khmer
    0.70
    ㎢
    0.70
     Buchstaben
    0.69
     Mem
    0.69
     Meme
    0.68
    POSITIVE LOGITS
    FOR
    1.05
    For
    0.88
    I
    0.82
     ve
    0.82
    Ive
    0.80
     FOR
    0.80
     fo
    0.76
    Fore
    0.76
    ForItem
    0.74
    Til
    0.72
    Activations Density 0.000%

    No Known Activations