© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89572
    Prev
    Next
    INDEX
    Explanations

    names followed by context

    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_3_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
    f
    0.94
    b
    0.93
    س
    0.87
    v
    0.85
    g
    0.80
    d
    0.77
    HQ
    0.76
    म
    0.76
    고
    0.75
    い
    0.75
    POSITIVE LOGITS
     of
    0.66
    of
    0.64
     ekki
    0.60
    that
    0.59
     ми
    0.58
    )。
    0.58
    ۳
    0.58
     система
    0.57
    没有人
    0.57
    3
    0.55
    Activations Density 0.000%

    No Known Activations