© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241332
    Prev
    Next
    INDEX
    Explanations

    start of response

    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_25_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
     չ
    0.45
    éc
    0.40
     Large
    0.39
     Sample
    0.38
     Drucker
    0.38
     Needham
    0.37
    !!!
    0.37
     Purs
    0.36
     Paper
    0.36
     LI
    0.36
    POSITIVE LOGITS
     historic
    0.38
     бір
    0.37
     behandling
    0.37
    vertexBuffer
    0.37
    低的
    0.36
    ".*:
    0.36
     그리고
    0.36
     रस्त
    0.36
     comodidad
    0.36
    ſſ
    0.36
    Activations Density 0.007%

    No Known Activations