© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36467
    Prev
    Next
    INDEX
    Explanations

    arm64 asm code

    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_3_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
    ką
    0.93
    were
    0.92
     চাহিয়া
    0.88
    isempty
    0.85
    kowe
    0.84
    𝗳
    0.84
    
    0.82
    𝘇
    0.81
    𝔀
    0.80
    ሖ
    0.80
    POSITIVE LOGITS
    </h3>
    1.22
    <0x0D>
    1.10
    </h4>
    0.97
    </h2>
    0.96
    </b>
    0.96
    ↵
    0.96
    </h1>
    0.93
    ↵↵↵
    0.92
    ↵↵
    0.91
    </h6>
    0.90
    Activations Density 0.009%

    No Known Activations