© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52563
    Prev
    Next
    INDEX
    Explanations

    comfort/clean

    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_55_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
    UtcNow
    0.43
    Staying
    0.42
     Virol
    0.40
    ântul
    0.40
     Seminar
    0.40
    ঠ
    0.39
     Bye
    0.39
    涝
    0.39
     Pvt
    0.38
     Engaging
    0.38
    POSITIVE LOGITS
     komfort
    0.43
    烟
    0.41
     right
    0.41
     RIGHT
    0.40
     centrally
    0.40
     smoker
    0.39
     smoky
    0.39
     smoking
    0.38
     काफ
    0.38
     الصغيرة
    0.37
    Activations Density 0.001%

    No Known Activations