© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43578
    Prev
    Next
    INDEX
    Explanations

    police, streets, conflict, political situation

    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
    t
    0.43
     es
    0.38
    ITARY
    0.38
     botanical
    0.38
    ad
    0.37
    ia
    0.37
    صح
    0.37
    is
    0.36
    AL
    0.36
     art
    0.36
    POSITIVE LOGITS
     Indones
    0.44
    🦴
    0.43
     Salaries
    0.41
    🦦
    0.40
     Испа
    0.39
     Faced
    0.39
     たち
    0.39
     Effekt
    0.39
    మే
    0.38
    詰
    0.38
    Activations Density 0.001%

    No Known Activations