© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219264
    Prev
    Next
    INDEX
    Explanations

    place names

    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_47_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
    Frame
    0.42
     Frame
    0.41
     dulu
    0.41
    ٹنے
    0.40
    asus
    0.40
     뜨
    0.40
    aside
    0.40
     hot
    0.39
    èce
    0.39
    ጾ
    0.38
    POSITIVE LOGITS
     SupCt
    0.39
     六
    0.38
     Luc
    0.38
     Papa
    0.38
    兩
    0.37
     Sa
    0.37
     Iv
    0.37
    及ひ
    0.37
     mommy
    0.37
    第六
    0.36
    Activations Density 0.002%

    No Known Activations