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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 34382
    Prev
    Next
    INDEX
    Explanations

    \

    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_7_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
    ﺪ
    1.09
    ین
    0.93
     nghệ
    0.84
    ᱔
    0.84
    s
    0.84
    持つ
    0.80
    ления
    0.79
    и
    0.77
    ﻠ
    0.75
     политики
    0.74
    POSITIVE LOGITS
    </h3>
    1.49
    </h2>
    1.18
    ↵↵↵
    1.11
    </strong>
    1.07
    ↵↵
    1.01
    </h1>
    1.01
    </h4>
    1.01
    </em>
    0.93
    </h6>
    0.92
    </sub>
    0.91
    Activations Density 0.001%

    No Known Activations