© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13613
    Prev
    Next
    INDEX
    Explanations

    jazz, debate, saxophone

    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_13_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
    at
    0.81
    Closed
    0.59
    저
    0.58
    Course
    0.58
    since
    0.56
    editors
    0.55
    징
    0.54
    I
    0.54
    ([
    0.54
    istance
    0.52
    POSITIVE LOGITS
     radish
    0.59
     hakk
    0.57
     nutri
    0.57
     ingen
    0.57
     hurricane
    0.54
     WLAN
    0.53
     sandalwood
    0.53
     gesture
    0.52
     naran
    0.52
     espont
    0.51
    Activations Density 0.001%

    No Known Activations