© 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-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 118708
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_27_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
     recent
    0.32
     최근
    0.30
     recently
    0.30
    bote
    0.30
     kt
    0.29
    According
    0.29
    <b>
    0.28
    Recent
    0.28
    Recently
    0.28
    Nice
    0.28
    POSITIVE LOGITS
     Ս
    0.33
    咡
    0.31
     மீண்டும்
    0.31
     assistenza
    0.30
    قى
    0.30
     ফ্রান্স
    0.29
    Ꮏ
    0.29
    ാനാ
    0.28
     mantan
    0.28
    Assalamualaikum
    0.27
    Activations Density 0.001%

    No Known Activations