© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14651
    Prev
    Next
    INDEX
    Explanations

    reach out for help

    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
     પો
    0.43
    ☮
    0.38
    疟
    0.38
     call
    0.37
     στοι
    0.37
     Callum
    0.36
     राष्ट्र
    0.36
     recourse
    0.36
     temat
    0.35
     calls
    0.35
    POSITIVE LOGITS
    list
    0.45
     lista
    0.44
     liste
    0.44
    LIST
    0.44
     Liste
    0.42
     list
    0.42
     u
    0.42
     தட
    0.40
     لیست
    0.39
    elist
    0.39
    Activations Density 0.014%

    No Known Activations