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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261355
    Prev
    Next
    INDEX
    Explanations

    compara con

    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_5_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
    K
    1.38
    </h3>
    1.30
    </h2>
    1.28
    </a>
    1.27
    1.20
     an
    1.19
    </h6>
    1.14
     are
    1.13
    </li>
    1.09
    ];
    1.09
    POSITIVE LOGITS
    yı
    1.41
    تي
    1.35
    을
    1.33
    이란
    1.20
    ти
    1.14
    т
    1.13
    त
    1.13
    тни
    1.13
    하여
    1.09
    یی
    1.09
    Activations Density 0.000%

    No Known Activations