© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152449
    Prev
    Next
    INDEX
    Explanations

    modulo / structure / data format / constructors

    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
    Pierre
    0.38
    ```
    0.37
    intendent
    0.36
    asmine
    0.35
    IVERS
    0.35
     mesma
    0.35
    ग्
    0.34
    SAME
    0.34
     tòa
    0.34
    оти
    0.34
    POSITIVE LOGITS
     getText
    0.40
     তপ
    0.39
     Modulation
    0.37
    patients
    0.37
    icyclic
    0.36
     modulate
    0.36
    ๙
    0.36
     kinetic
    0.36
     kä
    0.36
    这类
    0.36
    Activations Density 0.027%

    No Known Activations