© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203292
    Prev
    Next
    INDEX
    Explanations

    served delicious food

    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_6_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
    1.09
    ן
    1.02
     ي
    0.88
     forgo
    0.85
    <0x0D>
    0.83
     работа
    0.83
    ﻢ
    0.83
     reprim
    0.78
    ר
    0.78
     euthan
    0.76
    POSITIVE LOGITS
    ด
    1.32
    ل
    1.23
    c
    1.12
    л
    1.11
    v
    1.09
    ون
    1.06
    1
    1.06
    ів
    1.05
    ز
    1.01
    ку
    1.00
    Activations Density 0.000%

    No Known Activations