© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132258
    Prev
    Next
    INDEX
    Explanations

    field

    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_50_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
    वाय
    0.41
    㠻
    0.39
     khăn
    0.36
    ponential
    0.35
    ஆ
    0.35
    暦
    0.35
    㠃
    0.35
    ้อย
    0.34
    聪
    0.34
    䚲
    0.34
    POSITIVE LOGITS
    lds
    1.08
    ld
    1.07
     ld
    1.05
    LD
    1.03
     LD
    1.01
    ild
    0.99
     Ald
    0.96
     ald
    0.92
    eld
    0.91
     फ़
    0.90
    Activations Density 0.006%

    No Known Activations