© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175533
    Prev
    Next
    INDEX
    Explanations

    browser is closed

    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_20_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
     Ministry
    0.46
    舷
    0.43
    Ministry
    0.42
    erg
    0.42
     Министерство
    0.41
     Erg
    0.39
     Department
    0.38
    Department
    0.38
     Vest
    0.38
    楼
    0.38
    POSITIVE LOGITS
    लेषण
    0.42
     withhold
    0.40
    屏蔽
    0.40
    מית
    0.40
    ко
    0.39
     overwrite
    0.39
     teleport
    0.39
     terceiro
    0.39
    CLOUD
    0.38
    EtOH
    0.38
    Activations Density 0.003%

    No Known Activations