© 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. 203179
    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
     Undang
    0.61
     pravil
    0.57
     peraturan
    0.57
     efectuar
    0.56
    "
    0.56
     любые
    0.56
    ו
    0.55
    ాన్
    0.54
     Pasal
    0.54
    де
    0.54
    POSITIVE LOGITS
    ire
    0.58
     և
    0.55
    isc
    0.54
    irá
    0.53
    aten
    0.53
    cz
    0.52
    stå
    0.52
    arynx
    0.52
    istas
    0.50
     qualit
    0.50
    Activations Density 0.000%

    No Known Activations