© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203660
    Prev
    Next
    INDEX
    Explanations

    questions "what" and "are"

    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_25_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
     rapper
    0.40
     rappers
    0.40
    뀔
    0.40
     gamer
    0.40
     declaraciones
    0.40
    样例
    0.38
     projets
    0.38
     arbres
    0.38
     desafío
    0.37
     documentaries
    0.37
    POSITIVE LOGITS
     แต่
    0.41
     ఒ
    0.39
     เพราะ
    0.37
    ++
    0.35
     まず
    0.35
    Improved
    0.35
    som
    0.35
     만족
    0.35
    ~
    0.35
    omass
    0.35
    Activations Density 0.004%

    No Known Activations