© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139212
    Prev
    Next
    INDEX
    Explanations

    throw away

    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_12_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
     gasolina
    0.61
    IGAN
    0.61
     WASTE
    0.58
     odpad
    0.57
    㣱
    0.56
    OLINA
    0.55
     पीएच
    0.54
    ALK
    0.53
     residuos
    0.52
    Waste
    0.52
    POSITIVE LOGITS
     g
    0.62
    =
    0.61
     \
    0.57
     want
    0.56
     champions
    0.56
     stepped
    0.54
     champion
    0.53
     championed
    0.52
     k
    0.51
     wanted
    0.51
    Activations Density 0.001%

    No Known Activations