© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    िरी
    0.47
    ohist
    0.44
    ophyllum
    0.44
     upl
    0.44
     )-
    0.44
    chnitten
    0.43
    ැල
    0.43
     kalan
    0.43
     pockets
    0.42
    ন্দর
    0.42
    POSITIVE LOGITS
     FODC
    0.46
    `.
    0.45
    OD
    0.45
     hacía
    0.45
    係
    0.44
     gráf
    0.43
    গ্রাফ
    0.42
    ΑΣ
    0.42
    <unused2165>
    0.41
     unsurprisingly
    0.41
    Activations Density 0.000%

    No Known Activations