© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155087
    Prev
    Next
    INDEX
    Explanations

    artist

    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
     సామ
    0.40
     cl
    0.38
     inoculum
    0.38
    RUP
    0.38
    傻
    0.38
     سامان
    0.37
    će
    0.37
    聋
    0.37
    রাষ্ট্রমন্ত্রী
    0.37
     সালমান
    0.36
    POSITIVE LOGITS
     res
    0.39
    Runs
    0.39
    tensor
    0.38
    han
    0.38
     runs
    0.38
    jr
    0.37
    chis
    0.37
    Sw
    0.37
    Per
    0.37
    Wy
    0.36
    Activations Density 0.000%

    No Known Activations