© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86549
    Prev
    Next
    INDEX
    Explanations

    amplifier connectivity and function

    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_18_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
     그의
    0.21
     Jeho
    0.21
     мело
    0.20
     Jego
    0.20
     Uwe
    0.20
     AppBsky
    0.20
    يته
    0.19
    Ի
    0.19
     pInBuffer
    0.19
     Его
    0.19
    POSITIVE LOGITS
     patients
    0.19
    patient
    0.19
     blurring
    0.19
     meanings
    0.18
     dividing
    0.17
     encir
    0.17
    ਘ
    0.17
    治理
    0.17
     dismantling
    0.17
     patient
    0.17
    Activations Density 0.002%

    No Known Activations