© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61982
    Prev
    Next
    INDEX
    Explanations

    own you / own this / own your / own houses

    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_11_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
     on
    0.37
     of
    0.36
    endum
    0.34
     lays
    0.34
     vanqu
    0.33
    м
    0.33
    </h3>
    0.33
    se
    0.33
    ela
    0.33
     persuade
    0.33
    POSITIVE LOGITS
    ხვა
    0.38
    Bihar
    0.36
    O
    0.35
    Miami
    0.35
    trashButton
    0.34
    이드
    0.34
    ோ
    0.34
    urbation
    0.33
    Billboard
    0.33
    그
    0.33
    Activations Density 0.003%

    No Known Activations