© 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. 207297
    Prev
    Next
    INDEX
    Explanations

    April

    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
     ઘ
    0.40
     সেপ্ট
    0.40
    November
    0.39
     नवम्बर
    0.39
     fiche
    0.39
    嗟
    0.38
    headlines
    0.38
    漃
    0.38
     अवश्य
    0.37
     faid
    0.36
    POSITIVE LOGITS
     April
    1.02
     spring
    0.99
     봄
    0.93
    April
    0.91
     अप्रैल
    0.91
     Spring
    0.90
    春天
    0.90
     april
    0.89
     APRIL
    0.89
     springtime
    0.89
    Activations Density 0.002%

    No Known Activations