© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 229977
    Prev
    Next
    INDEX
    Explanations

    brittleness

    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
     in
    1.53
    </h2>
    1.09
     about
    1.07
     It
    1.02
     t
    1.01
     at
    1.00
     into
    0.98
     is
    0.98
     an
    0.96
    ized
    0.95
    POSITIVE LOGITS
    lcii
    1.05
    6
    1.05
    ל
    0.96
    8
    0.95
    고
    0.95
    지
    0.94
    𝓭
    0.92
    ด์
    0.91
    ន្ថ
    0.90
    る
    0.90
    Activations Density 0.000%

    No Known Activations