© 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. 175684
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Bri
    0.40
    民
    0.40
    Britt
    0.39
    拼
    0.38
     &-
    0.38
    ហ
    0.37
    ኪ
    0.37
     bri
    0.37
     Ian
    0.36
     smugg
    0.36
    POSITIVE LOGITS
     W
    0.54
    reen
    0.49
     ال
    0.43
    W
    0.43
    ab
    0.41
    ingen
    0.40
    Ｗ
    0.40
    wender
    0.38
    inger
    0.38
     ওষুধ
    0.38
    Activations Density 0.000%

    No Known Activations