© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218153
    Prev
    Next
    INDEX
    Explanations

    substack.com links

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    parts of URLs, especially `.substack.com` and domain components like `.com` and `p`, along with some present-tense verbs ending in 'ing'.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     ২০১৭
    0.39
     геометри
    0.38
    Palindrome
    0.38
    /]
    0.38
    SESSION
    0.37
    Date
    0.37
    स्टूड
    0.37
    讲
    0.37
    இல்
    0.37
    stige
    0.37
    POSITIVE LOGITS
     lofty
    0.36
     NSA
    0.35
     MTN
    0.35
     eul
    0.35
     quietly
    0.34
     bait
    0.34
     IBOutlet
    0.34
     পড়েন
    0.33
     Rehman
    0.33
    ɚ
    0.33
    Activations Density 0.001%

    No Known Activations