© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4533
    Prev
    Next
    INDEX
    Explanations

    context window sizes

    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_40_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
     بخوان
    0.38
    abilis
    0.37
    mort
    0.37
    ケル
    0.36
     स्टैंड
    0.36
    timetable
    0.35
    )&=
    0.35
    beg
    0.35
    ajjati
    0.34
    otechnical
    0.34
    POSITIVE LOGITS
     зачем
    0.38
    Added
    0.37
    veillance
    0.36
     emergencies
    0.36
    ჩ
    0.36
     Mig
    0.36
     дополнительные
    0.35
    docs
    0.34
    Hidden
    0.34
     cim
    0.34
    Activations Density 0.058%

    No Known Activations