© 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
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97226
    Prev
    Next
    INDEX
    Explanations

    DSM-5 diagnostic manual

    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_14_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
    </code>
    0.59
    </a>
    0.58
    ін
    0.55
    ър
    0.53
    </li>
    0.52
    цеп
    0.50
    </span>
    0.50
    icent
    0.48
    inus
    0.47
    格
    0.47
    POSITIVE LOGITS
     Europese
    0.63
     Chirurg
    0.60
     Encycl
    0.60
    j
    0.58
    :
    0.57
     CRIMINAL
    0.56
    মিক্যাল
    0.55
     américaine
    0.55
     Economía
    0.54
     correto
    0.54
    Activations Density 0.002%

    No Known Activations