© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78646
    Prev
    Next
    INDEX
    Explanations

    cultivars, овощи, фрукты, выбором

    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_0_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
    م
    1.91
    м
    1.86
    ي
    1.72
    ม
    1.61
    いる
    1.59
    ्स
    1.56
    ות
    1.48
    い
    1.46
    نان
    1.43
    น้ำ
    1.40
    POSITIVE LOGITS
    c
    1.91
    S
    1.49
    0
    1.38
    x
    1.34
    p
    1.31
    l
    1.28
    R
    1.26
    B
    1.24
    ci
    1.20
    U
    1.20
    Activations Density 0.000%

    No Known Activations