© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18236
    Prev
    Next
    INDEX
    Explanations

    pygame module imports

    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_34_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
    upani
    0.40
    <0xB7>
    0.37
     acorn
    0.37
     gallium
    0.37
     Bento
    0.36
    回到
    0.35
    返回
    0.35
    ajari
    0.35
    collide
    0.34
    还原
    0.34
    POSITIVE LOGITS
     👍
    0.35
    歓
    0.35
     relevantes
    0.35
    מות
    0.34
    sd
    0.33
     fett
    0.33
     সূরা
    0.33
     зда
    0.33
    㖡
    0.32
    敂
    0.32
    Activations Density 0.007%

    No Known Activations