© 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. 36770
    Prev
    Next
    INDEX
    Explanations

    (

    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
    们
    0.44
    ներ
    0.42
    ھیں
    0.40
    들이
    0.38
    們
    0.38
    茵
    0.37
    들과
    0.37
    㫧
    0.37
     "-",
    0.36
    ாளர்க
    0.35
    POSITIVE LOGITS
    }).
    0.40
     Goldsmith
    0.39
    dyl
    0.38
    uerra
    0.37
    មុខ
    0.36
    ্ডি
    0.36
    ujuan
    0.36
    ithe
    0.35
     goo
    0.35
    вање
    0.35
    Activations Density 0.000%

    No Known Activations