© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 261084
    Prev
    Next
    INDEX
    Explanations

    GR / GRN / FGR / PGR / PGT / FGRBP

    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
    u
    1.77
    on
    1.13
    </h3>
    1.05
     Statue
    1.01
     Sharks
    0.99
     CCN
    0.93
     State
    0.91
    uot
    0.91
     Thoroughbred
    0.91
     Thatcher
    0.90
    POSITIVE LOGITS
    '
    1.34
    ال
    1.20
    い
    1.17
    ید
    1.15
    \
    1.15
    ২০
    1.14
    ும்
    1.08
    ۲
    1.08
    ون
    1.07
     погиб
    1.07
    Activations Density 0.000%

    No Known Activations