© 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. 178736
    Prev
    Next
    INDEX
    Explanations

    hojas

    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
     ति
    0.41
     wr
    0.41
     mos
    0.40
     Ти
    0.38
    ede
    0.38
    vena
    0.38
     tif
    0.38
    変
    0.37
     inflammation
    0.37
    नै
    0.37
    POSITIVE LOGITS
     Ho
    1.00
     ho
    0.98
    Ho
    0.98
    ho
    0.89
     HO
    0.82
     хо
    0.82
    HO
    0.74
    호
    0.71
     호
    0.69
     हो
    0.68
    Activations Density 0.008%

    No Known Activations