© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34969
    Prev
    Next
    INDEX
    Explanations

    month, numbers, or specific types of text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bacteri
    0.39
     zape
    0.38
     الط
    0.37
    𝕙
    0.36
    WhatsApp
    0.35
     Tym
    0.35
    Af
    0.35
    र्श
    0.35
    CHD
    0.35
    ཏ
    0.35
    POSITIVE LOGITS
    minor
    0.40
     ব্রাহ্ম
    0.39
    罚
    0.38
    ্লিক
    0.36
    贸
    0.36
     minor
    0.36
    oble
    0.35
     सीधी
    0.35
    FFIC
    0.35
     vendita
    0.35
    Activations Density 0.001%

    No Known Activations