© 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. 131084
    Prev
    Next
    INDEX
    Explanations

    million tokens

    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
     حق
    0.26
     خود
    0.25
     ciudadanos
    0.25
     ض
    0.25
     authorize
    0.25
     كيفية
    0.24
     ध
    0.23
     predictability
    0.23
    ناط
    0.23
     But
    0.23
    POSITIVE LOGITS
     reformation
    0.25
    ልቅ
    0.24
    Melitaea
    0.23
     объем
    0.23
     lọ
    0.23
    事业
    0.23
    𝙰
    0.23
    Компания
    0.23
     Troll
    0.23
    4
    0.23
    Activations Density 0.004%

    No Known Activations