© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53420
    Prev
    Next
    INDEX
    Explanations

    top or leading

    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_55_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
     Wendell
    0.43
    detalle
    0.39
    冈
    0.38
     Unido
    0.37
    咙
    0.37
    ামো
    0.37
    嬷
    0.37
    者的
    0.37
    quickly
    0.36
    上的
    0.36
    POSITIVE LOGITS
     hub
    0.44
     leading
    0.39
     inoculum
    0.38
    LEADING
    0.38
     Energ
    0.38
     HUB
    0.37
     Mast
    0.36
     оправ
    0.35
    hub
    0.35
    AGN
    0.34
    Activations Density 0.025%

    No Known Activations