© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48693
    Prev
    Next
    INDEX
    Explanations

    * of / is a

    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_31_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
     цик
    0.44
     cycle
    0.40
     cycles
    0.39
    blest
    0.37
     reasonable
    0.37
     ciclo
    0.37
     LPC
    0.37
    벌
    0.37
     لح
    0.36
     CEM
    0.35
    POSITIVE LOGITS
    belongs
    0.39
     технология
    0.38
    蒂
    0.38
    下來
    0.38
     ори
    0.37
    belong
    0.37
    Тех
    0.36
     বাসিন্দ
    0.35
     te
    0.35
    utches
    0.35
    Activations Density 0.008%

    No Known Activations