© 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. 141339
    Prev
    Next
    INDEX
    Explanations

    code structure and values

    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_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
    BeforeCall
    0.61
     atau
    0.59
     அல்லது
    0.59
     или
    0.57
    㡷
    0.56
     तसेच
    0.56
     நுரைய
    0.56
     Tattha
    0.55
     Ettha
    0.54
     hoặc
    0.54
    POSITIVE LOGITS
    '
    0.55
     Rob
    0.50
     évidemment
    0.48
     increment
    0.48
    να
    0.48
     collier
    0.48
    ブ
    0.47
     traduit
    0.47
     enseignants
    0.46
    štění
    0.46
    Activations Density 0.001%

    No Known Activations