© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158916
    Prev
    Next
    INDEX
    Explanations

    Gardens

    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_2_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
    ۔
    1.63
     i
    1.33
    ।
    1.32
    स
    1.27
    ر
    1.25
    ي
    1.24
    ج
    1.24
    ม
    1.19
     l
    1.16
    of
    1.13
    POSITIVE LOGITS
    l
    1.05
    as
    1.02
    我
    0.91
    ून
    0.91
    ளை
    0.90
    都
    0.89
    PERCENT
    0.88
    LENGTH
    0.88
    POST
    0.86
    ier
    0.86
    Activations Density 0.000%

    No Known Activations