© 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. 56669
    Prev
    Next
    INDEX
    Explanations

    'pâté', 'liver', 'duck', 'goose'

    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
     solutions
    0.59
     columns
    0.58
             
    0.54
     groups
    0.54
     hydrogen
    0.54
            
    0.53
     liqueur
    0.53
    )
    0.53
     breakfasts
    0.52
     estimate
    0.52
    POSITIVE LOGITS
    F
    0.59
    angered
    0.57
     ላ
    0.54
    లేదు
    0.54
    异常
    0.53
    人性
    0.52
    f
    0.52
    𝚒
    0.52
    लैंड
    0.52
    등급
    0.51
    Activations Density 0.002%

    No Known Activations