© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 206210
    Prev
    Next
    INDEX
    Explanations

    about topics

    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_25_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
    zeption
    0.22
    📙
    0.22
    ेंद
    0.21
     بالإضافة
    0.20
     معیار
    0.20
    द्रता
    0.20
     Parlamento
    0.20
     Transvaal
    0.20
     teinte
    0.20
    ises
    0.20
    POSITIVE LOGITS
     SMITH
    0.19
     sosok
    0.19
    真是
    0.17
    進
    0.17
     אני
    0.17
    瑤
    0.17
    Smith
    0.17
     quelque
    0.17
    の一
    0.16
     reluctance
    0.16
    Activations Density 0.032%

    No Known Activations