© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45153
    Prev
    Next
    INDEX
    Explanations

    C++ code and versions

    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_22_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
    安置
    0.38
     instead
    0.38
    instead
    0.37
     affirmat
    0.37
    }$
    0.36
    ิทธิ์
    0.36
     insist
    0.36
    าลัย
    0.36
     coexistence
    0.35
    鹿
    0.35
    POSITIVE LOGITS
     प्रभाव
    0.43
     davranış
    0.41
    抔
    0.41
     Teatro
    0.41
    聚集
    0.40
     ऐतिहासिक
    0.40
    iculo
    0.40
     cittam
    0.39
     Bacteriol
    0.39
     Hard
    0.39
    Activations Density 0.001%

    No Known Activations