© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122635
    Prev
    Next
    INDEX
    Explanations

    walks and navigation

    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_37_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
     Celebration
    0.44
    λια
    0.42
    れます
    0.41
    ক্লো
    0.41
    ᄋ
    0.41
    읍
    0.40
    OBI
    0.39
    enches
    0.38
     cellspacing
    0.38
    IAA
    0.38
    POSITIVE LOGITS
    retr
    0.38
    TakePicture
    0.38
     retr
    0.37
    వాన్ని
    0.37
     mobility
    0.36
    걀
    0.36
    
    0.35
     detective
    0.35
    Sear
    0.35
     compensation
    0.35
    Activations Density 0.001%

    No Known Activations