© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87402
    Prev
    Next
    INDEX
    Explanations

    actions consequences

    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_23_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
     kula
    0.21
    ulas
    0.21
    ula
    0.21
    вам
    0.20
     ニ
    0.20
    لاسه
    0.20
     kusal
    0.20
    ulo
    0.20
    我們要
    0.19
     कूल
    0.19
    POSITIVE LOGITS
    めの
    0.21
     ENO
    0.21
     rund
    0.21
    messaging
    0.21
     Reboot
    0.20
     giúp
    0.20
     ROI
    0.19
    盈
    0.19
    Print
    0.19
     বার্তা
    0.18
    Activations Density 0.004%

    No Known Activations