© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243259
    Prev
    Next
    INDEX
    Explanations

    Gizmos and rotation

    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_40_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
    წ
    0.35
    option
    0.35
    expandedTitle
    0.35
    💪
    0.34
     Christ
    0.34
    দ্র
    0.34
     norma
    0.34
    ⏳
    0.34
    msup
    0.34
     elongated
    0.33
    POSITIVE LOGITS
     creada
    0.44
     imagery
    0.39
     adjoining
    0.38
     airfield
    0.38
     Shelter
    0.38
     criada
    0.38
     cemetery
    0.38
    :/
    0.38
     crée
    0.38
    PDP
    0.37
    Activations Density 0.001%

    No Known Activations