© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214374
    Prev
    Next
    INDEX
    Explanations

    escape room

    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_5_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
    ુ
    1.34
     criticized
    1.11
     consejos
    1.11
     ও
    1.10
    O
    1.09
     criticised
    1.06
    人
    1.04
     marques
    1.01
    ле
    0.99
    こと
    0.99
    POSITIVE LOGITS
    ம்
    0.96
    ları
    0.96
    م
    0.94
    DS
    0.92
    ian
    0.89
    ALL
    0.86
     Sonnen
    0.85
     War
    0.85
    mem
    0.84
    fj
    0.84
    Activations Density 0.000%

    No Known Activations