© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131984
    Prev
    Next
    INDEX
    Explanations

    briefing

    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_6_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
    ين
    1.38
    एम
    1.23
    ت
    1.22
    it
    1.19
    ㍍
    1.08
    يد
    1.05
    т
    1.01
    im
    0.98
     ဖ
    0.97
    тят
    0.97
    POSITIVE LOGITS
    .
    1.05
    ;
    0.91
    וד
    0.69
    اد
    0.67
    Clinic
    0.65
    OL
    0.64
    2
    0.64
    in
    0.63
    substring
    0.63
    1
    0.63
    Activations Density 0.000%

    No Known Activations