© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ’
    2.31
    ।’
    1.57
    '
    1.47
    ’)
    1.45
    ।'
    1.39
    )'
    1.23
    “
    1.20
    ’-
    1.18
    २
    1.18
    >
    1.16
    POSITIVE LOGITS
    in
    1.34
    ai
    1.14
    لي
    1.10
    toList
    1.09
    ot
    1.05
    نا
    1.05
    durch
    1.05
     Кли
    1.02
    ia
    1.02
     Пре
    1.02
    Activations Density 0.000%

    No Known Activations