© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2425
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and definitions

    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_39_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
    禹
    0.38
     errorHandler
    0.37
    ائو
    0.37
    MQTT
    0.37
    ixar
    0.36
    ikki
    0.36
    opensource
    0.36
     pouls
    0.35
    雓
    0.35
    anner
    0.35
    POSITIVE LOGITS
     Definition
    0.54
     definition
    0.46
     definición
    0.44
     डेफिनेशन
    0.43
     targeting
    0.42
     Definitions
    0.42
    Definition
    0.42
     definitions
    0.41
     Define
    0.40
     defini
    0.40
    Activations Density 0.075%

    No Known Activations