© 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
    2. Gemma-3-27B-IT
    3. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 90552
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    </h3>
    0.72
    </code>
    0.72
    </strong>
    0.68
    </b>
    0.68
    </h1>
    0.65
    </h4>
    0.55
    </h2>
    0.54
    .
    0.54
     and
    0.53
    ,
    0.53
    POSITIVE LOGITS
    <em>
    0.66
    <i>
    0.64
    ርድ
    0.46
    thousands
    0.46
     $)$.
    0.39
    )-\
    0.37
     Peb
    0.37
    𝑣
    0.37
    Colors
    0.36
     Fore
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.