© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203206
    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_12_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
     ActivityCompat
    0.28
     এখানে
    0.25
     Edna
    0.25
     sabbam
    0.24
    ä
    0.24
    tics
    0.24
    Indonesia
    0.24
     एवरी
    0.23
     Guadeloupe
    0.23
     यहां
    0.23
    POSITIVE LOGITS
    '
    0.30
    ็ง
    0.20
    ()'
    0.20
     Pourquoi
    0.20
    selling
    0.20
     conceding
    0.20
    ոն
    0.19
     welke
    0.19
    quir
    0.19
    čen
    0.19
    Activations Density 0.000%

    No Known Activations