© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170383
    Prev
    Next
    INDEX
    Explanations

    AI programmed response

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     unload
    0.47
     unloaded
    0.41
    atas
    0.40
    unload
    0.40
     unloading
    0.39
    fer
    0.38
    କ
    0.38
    FER
    0.37
    CA
    0.37
    HW
    0.36
    POSITIVE LOGITS
    ரிக்கை
    0.46
     кома
    0.39
     touche
    0.38
    гана
    0.38
    സ്തു
    0.37
    恻
    0.37
    দিষ্ট
    0.36
     stately
    0.36
    పీ
    0.36
    ికె
    0.36
    Activations Density 0.005%

    No Known Activations