Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261476
    Prev
    Next
    INDEX
    Explanations

    verb endings -ó, -ado, -udo, -uta, -uda

    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
    <0x0D>
    1.41
    ot
    1.02
    </a>
    0.98
    ra
    0.98
    2
    0.97
    </h3>
    0.96
    </h4>
    0.96
    </strong>
    0.96
    ším
    0.95
    </h1>
    0.91
    POSITIVE LOGITS
    of
    1.45
    其他
    1.06
    الت
    1.05
    та
    1.05
    It
    1.05
    说
    1.05
    ts
    1.04
    项目
    1.03
    cs
    1.02
    对象
    1.02
    Activations Density 0.001%

    No Known Activations