© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200667
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    蹋
    0.42
    "){
    0.41
    ન્ટે
    0.39
    ləş
    0.38
    ]][
    0.37
    ീകരിക്ക
    0.36
    ionati
    0.36
    ṕ
    0.35
    ↵↵↵
    0.35
     quelles
    0.35
    POSITIVE LOGITS
    了一个
    0.44
    了一個
    0.39
    了一
    0.38
    了好
    0.38
    သူ
    0.37
    lı
    0.37
     unto
    0.36
    دی
    0.36
     continuing
    0.36
    하다
    0.35
    Activations Density 0.066%

    No Known Activations