© 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. 155601
    Prev
    Next
    INDEX
    Explanations

    author or title

    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
    œur
    0.49
     Air
    0.44
    ᕇ
    0.42
     filter
    0.40
     noise
    0.40
     heur
    0.40
    oureux
    0.39
    ಧ್ಯ
    0.39
     dense
    0.38
    گیر
    0.38
    POSITIVE LOGITS
    K
    0.42
     K
    0.42
    ട്ടു
    0.41
     Sak
    0.40
     пан
    0.39
    atiti
    0.39
    Sak
    0.38
     transactional
    0.38
    شكال
    0.38
    displaystyle
    0.37
    Activations Density 0.000%

    No Known Activations