© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197546
    Prev
    Next
    INDEX
    Explanations

    4-bit, 8-bit quantization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     धोखा
    0.40
     সমস্যার
    0.38
     ቡ
    0.36
     列
    0.36
     проблемы
    0.35
     прибыль
    0.35
     проблема
    0.34
    FormControl
    0.34
    ROTTLE
    0.34
    ATL
    0.34
    POSITIVE LOGITS
     விதிக்க
    0.37
    واحد
    0.36
    ඕ
    0.36
     anek
    0.35
    sekut
    0.35
     betreff
    0.34
    łoż
    0.34
     poza
    0.34
     opro
    0.34
     multiplicado
    0.33
    Activations Density 0.008%

    No Known Activations