© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13096
    Prev
    Next
    INDEX
    Explanations

    knights and chivalry

    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_13_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
    чное
    0.53
     бывает
    0.52
    ");
    0.50
    мни
    0.47
    哴
    0.46
    AND
    0.46
    ");*/
    0.46
    Ố
    0.46
    on
    0.46
    Walt
    0.46
    POSITIVE LOGITS
     báo
    0.57
    잤
    0.54
     blackout
    0.54
     generator
    0.52
     général
    0.52
     breakfast
    0.51
     beneficiaries
    0.51
     d
    0.50
     사라
    0.50
     Generator
    0.50
    Activations Density 0.017%

    No Known Activations