© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107187
    Prev
    Next
    INDEX
    Explanations

    hadn't been

    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_2_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
    i
    1.33
    ي
    1.25
    ků
    1.13
    ات
    1.02
    కు
    0.98
    ká
    0.98
    isatie
    0.96
    يا
    0.92
     Fahrer
    0.86
    ২
    0.85
    POSITIVE LOGITS
     a
    1.55
    ार
    1.17
     o
    1.14
     i
    1.09
    )$
    1.09
    ר
    1.09
    ¹.
    1.09
    ອ
    1.07
    ک
    1.06
    \%)
    1.05
    Activations Density 0.001%

    No Known Activations