© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199670
    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_12_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
     multicolored
    0.60
     नौकर
    0.59
     شامل
    0.56
     Kondo
    0.56
     మొక్క
    0.55
     मुश्किलें
    0.55
    ƙ
    0.55
     वाले
    0.54
     ച
    0.54
     പ്രശ്
    0.54
    POSITIVE LOGITS
    ↵
    0.79
    ↵↵
    0.68
     That
    0.65
    </h3>
    0.61
     calculer
    0.58
    </i>
    0.52
    עם
    0.52
    </b>
    0.51
     And
    0.49
     THAT
    0.49
    Activations Density 0.000%

    No Known Activations