© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91387
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.5-flash-lite
    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
    TD
    0.46
    Amino
    0.42
    Cult
    0.42
    >
    0.42
    AP
    0.41
    мережа
    0.41
    Sh
    0.41
    Python
    0.41
    Flask
    0.41
    Wine
    0.40
    POSITIVE LOGITS
     More
    0.64
     The
    0.64
    </h1>
    0.58
     Back
    0.58
     Briefly
    0.57
    </blockquote>
    0.55
    </h3>
    0.54
     Start
    0.54
     Begin
    0.54
    </h2>
    0.53
    Activations Density 0.001%

    No Known Activations