© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84406
    Prev
    Next
    INDEX
    Explanations

    are a / an

    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_23_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
    protect
    0.50
    int
    0.41
    vertical
    0.40
     i
    0.38
    ite
    0.38
     derives
    0.38
     kinda
    0.37
    ik
    0.37
    anted
    0.36
    ism
    0.36
    POSITIVE LOGITS
    。「
    0.43
    盻
    0.41
     heur
    0.39
     গল্পের
    0.39
    غات
    0.39
     이에
    0.38
     môn
    0.38
    વાથી
    0.37
     kinet
    0.37
    érons
    0.37
    Activations Density 0.013%

    No Known Activations