© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110085
    Prev
    Next
    INDEX
    Explanations

    onslaught of unstoppable things

    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_2_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
    ת
    1.45
    ва
    1.43
    هي
    1.39
    ني
    1.30
    تين
    1.29
     chave
    1.28
    يد
    1.23
    ה
    1.22
    ס
    1.18
    ை
    1.15
    POSITIVE LOGITS
    In
    1.35
    ete
    1.33
    在
    1.30
    ุ
    1.29
    1
    1.21
    و
    1.18
    ाम
    1.14
    f
    1.13
    ishing
    1.12
    ो
    1.10
    Activations Density 0.001%

    No Known Activations