© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135186
    Prev
    Next
    INDEX
    Explanations

    Spanish, providing referrals

    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_37_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
     দুষ্ট
    0.42
    entie
    0.38
     ಔ
    0.37
     かわいい
    0.36
     বাই
    0.36
    scanning
    0.35
    摒
    0.35
     nœ
    0.35
     Bringing
    0.35
     दु
    0.35
    POSITIVE LOGITS
     vinho
    0.41
     rape
    0.39
     qualified
    0.38
     ধর্ষ
    0.37
    П
    0.36
     rewards
    0.36
     stigma
    0.35
    olk
    0.35
    setOnAction
    0.35
     क्वालीफ
    0.35
    Activations Density 0.001%

    No Known Activations