© 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. 132345
    Prev
    Next
    INDEX
    Explanations

    nb

    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
    تين
    1.05
    اتي
    0.94
    ర్
    0.93
    де
    0.91
    dır
    0.90
    elijke
    0.90
    ﻦ
    0.89
    تها
    0.88
    सँग
    0.88
    ด
    0.88
    POSITIVE LOGITS
     of
    1.11
    ain
    1.11
    and
    1.09
    \
    1.02
    <0x0D>
    1.01
    0
    0.98
     in
    0.98
    of
    0.96
    </h2>
    0.96
    ),
    0.91
    Activations Density 0.001%

    No Known Activations