© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205867
    Prev
    Next
    INDEX
    Explanations

    things

    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_46_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
    Accum
    0.36
    程
    0.35
    agle
    0.35
    ವರೆ
    0.34
    cznej
    0.34
    ემი
    0.33
     Huz
    0.33
    க்கூ
    0.32
    摷
    0.32
    त्रा
    0.32
    POSITIVE LOGITS
     things
    2.53
    Things
    2.25
     Things
    2.23
    things
    2.14
     THINGS
    2.08
     cosas
    2.06
     coisas
    2.05
     вещи
    1.90
     Dinge
    1.88
     вещей
    1.88
    Activations Density 0.171%

    No Known Activations