© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26195
    Prev
    Next
    INDEX
    Explanations

    seat adjustment, height, material

    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_10_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
    ن
    0.39
    ي
    0.36
    ย
    0.29
    вати
    0.27
    ch
    0.27
    i
    0.25
    ব
    0.25
    י
    0.25
    و
    0.25
    اکي
    0.24
    POSITIVE LOGITS
     dynamite
    0.24
     kom
    0.24
     vocals
    0.23
     o
    0.22
     klimat
    0.22
     singing
    0.21
     Buddh
    0.21
     Vogel
    0.21
     lời
    0.20
     biographies
    0.20
    Activations Density 0.004%

    No Known Activations