© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49915
    Prev
    Next
    INDEX
    Explanations

    approach and handling

    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_31_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
     sedangkan
    0.37
     wenn
    0.37
     hvis
    0.35
     dacă
    0.34
    如果是
    0.34
     ибо
    0.34
     فاذا
    0.34
    .([]
    0.33
     तोला
    0.33
     mence
    0.33
    POSITIVE LOGITS
     prevailed
    0.41
    ITS
    0.38
     Including
    0.37
     prevails
    0.37
    IT
    0.36
     exists
    0.36
    ophthal
    0.36
    </b>
    0.35
    œuvre
    0.35
     ITS
    0.34
    Activations Density 0.012%

    No Known Activations