© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230539
    Prev
    Next
    INDEX
    Explanations

    look at

    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_6_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
    ad
    1.30
    ب
    1.14
    re
    1.13
    ม
    1.12
    म
    1.09
    </h4>
    1.08
    KS
    1.07
    </h2>
    1.05
    ר
    1.05
    op
    1.04
    POSITIVE LOGITS
    一提
    1.12
    стве
    0.89
    पणे
    0.80
     dàng
    0.80
     менедже
    0.77
     поня
    0.75
    jate
    0.75
    \,\
    0.74
     avut
    0.74
     innovative
    0.72
    Activations Density 0.000%

    No Known Activations