© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92612
    Prev
    Next
    INDEX
    Explanations

    common

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     Back
    0.41
     justo
    0.38
     anis
    0.38
    的就是
    0.36
    ઊ
    0.35
     Side
    0.34
    Repos
    0.34
     `,
    0.34
     Shore
    0.34
     Hok
    0.34
    POSITIVE LOGITS
     common
    0.76
    Common
    0.70
     común
    0.70
     Common
    0.68
    common
    0.66
     comune
    0.65
     COMMON
    0.65
     comum
    0.64
     comunes
    0.64
     कॉमन
    0.60
    Activations Density 0.000%

    No Known Activations