© 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. 202379
    Prev
    Next
    INDEX
    Explanations

    apk

    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
    त
    1.40
    at
    1.37
    т
    1.34
    ви
    1.26
    м
    1.20
    il
    1.13
    ம்
    1.11
    р
    1.08
    م
    1.02
    ير
    1.01
    POSITIVE LOGITS
    0
    1.31
    -
    1.15
    ।’
    1.06
    \
    0.98
     \
    0.98
     adhesions
    0.98
    ll
    0.97
    ’,
    0.95
    {"
    0.95
     semiconductors
    0.95
    Activations Density 0.000%

    No Known Activations