© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155218
    Prev
    Next
    INDEX
    Explanations

    greetings and languages

    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_50_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
    tr
    0.53
    Tr
    0.49
     Tr
    0.48
     피
    0.47
    𝘫
    0.44
     सो
    0.43
     pis
    0.41
    Pis
    0.40
    ტრ
    0.40
     Moi
    0.39
    POSITIVE LOGITS
     ro
    0.44
     सा
    0.42
    บา
    0.41
    Bat
    0.41
    bate
    0.40
    स्पति
    0.40
     Fats
    0.40
     spade
    0.40
    abe
    0.39
    芎
    0.39
    Activations Density 0.037%

    No Known Activations