© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132655
    Prev
    Next
    INDEX
    Explanations

    places and entities

    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_50_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
     willful
    0.43
     Gori
    0.41
    William
    0.39
     गोपाल
    0.38
    铍
    0.38
     அடு
    0.38
     drawn
    0.37
     Balliye
    0.37
     Joan
    0.36
    вли
    0.36
    POSITIVE LOGITS
     M
    0.54
    グランド
    0.45
    legen
    0.45
    Conf
    0.44
     port
    0.44
     Northwest
    0.44
     Confederate
    0.43
     Su
    0.42
     cổng
    0.42
     Grand
    0.41
    Activations Density 0.010%

    No Known Activations