© 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. 53551
    Prev
    Next
    INDEX
    Explanations

    lower than

    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
     QnrB
    0.38
     users
    0.38
     użytk
    0.37
     позд
    0.36
     }{}_{\
    0.36
     Quickly
    0.35
     quickly
    0.34
     ursprünglich
    0.34
     ভীষণ
    0.33
     গবে
    0.33
    POSITIVE LOGITS
    لاع
    0.44
     conventional
    0.40
    एसएल
    0.39
     Conventional
    0.39
     convencional
    0.39
    陸
    0.39
    conventional
    0.38
    Malley
    0.37
    लैंड
    0.37
    枓
    0.36
    Activations Density 0.007%

    No Known Activations