© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45648
    Prev
    Next
    INDEX
    Explanations

    structured text (ST) programming

    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_13_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
     тканей
    0.16
     honti
    0.16
    Macros
    0.15
    Static
    0.15
     பளி
    0.15
    Identifier
    0.15
    I
    0.15
    ne
    0.14
    Coefficient
    0.14
    Baseline
    0.14
    POSITIVE LOGITS
     sosyal
    0.15
     worried
    0.14
     mete
    0.14
     sarebbe
    0.14
     building
    0.13
     quintessential
    0.13
     stara
    0.13
    тала
    0.13
     soziale
    0.13
    wicz
    0.13
    Activations Density 0.019%

    No Known Activations