© 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. 89018
    Prev
    Next
    INDEX
    Explanations

    Aruba

    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
    ו
    0.92
     matemáticas
    0.70
    по
    0.67
    것
    0.65
    льзя
    0.64
    ли
    0.63
    ahh
    0.63
    цию
    0.62
    larda
    0.62
     سيكون
    0.62
    POSITIVE LOGITS
    ون
    0.80
    </h3>
    0.76
    一
    0.70
    </td>
    0.69
    ）・
    0.69
    </h4>
    0.68
    </h1>
    0.67
    کی
    0.66
    up
    0.65
    中国
    0.64
    Activations Density 0.000%

    No Known Activations