© 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. 35727
    Prev
    Next
    INDEX
    Explanations

    places and travel

    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
     المره
    0.45
     Merge
    0.42
    ダ
    0.41
    冧
    0.40
     Bestand
    0.39
    acat
    0.39
     मर्ज
    0.39
     파인더
    0.39
     बीएसटीसी
    0.38
     മനസ്സ
    0.38
    POSITIVE LOGITS
     K
    0.54
     SDR
    0.50
    K
    0.46
     pe
    0.40
    ក
    0.40
     SDP
    0.39
    ക
    0.39
     EPI
    0.39
     rave
    0.38
     ক
    0.37
    Activations Density 0.001%

    No Known Activations