© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211684
    Prev
    Next
    INDEX
    Explanations

    детали

    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_5_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
    ва
    1.12
    کر
    1.08
     pelea
    1.08
     lintas
    1.05
    สุด
    1.05
     nostru
    1.05
     sede
    1.03
    ָ
    1.03
     seguenti
    1.02
    Ź
    1.02
    POSITIVE LOGITS
    و
    1.50
    ام
    1.38
    其他
    1.38
    از
    1.32
    nés
    1.23
    ifts
    1.20
    ر
    1.20
    ే
    1.20
    t
    1.19
    د
    1.17
    Activations Density 0.000%

    No Known Activations