© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202839
    Prev
    Next
    INDEX
    Explanations

    first line

    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_12_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
    ahead
    0.59
     만나
    0.57
     Ahead
    0.56
    ရော
    0.55
    高于
    0.54
     बचाता
    0.54
    ன
    0.54
    }.
    0.54
    ープ
    0.53
     फाइन
    0.52
    POSITIVE LOGITS
    Investment
    0.60
     Investment
    0.57
    agal
    0.55
    িল
    0.51
    Recipes
    0.51
    Image
    0.50
     similares
    0.49
     teclas
    0.48
    ंबू
    0.48
     বৃদ্ধির
    0.48
    Activations Density 0.008%

    No Known Activations