© 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. 45315
    Prev
    Next
    INDEX
    Explanations

    hydroponic, arteriosclerosis, trastuzumab, artificial intelligence, supply chain, tinnitus

    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
    omitempty
    0.21
    ರುವುದರಿಂದ
    0.21
     antisymmetric
    0.20
     gimbal
    0.20
     kadang
    0.19
    ☑
    0.19
     있게
    0.19
     cognizant
    0.19
    рим
    0.19
    ईद
    0.19
    POSITIVE LOGITS
    帮助
    0.22
     splashed
    0.22
    ?»
    0.20
     διάρκ
    0.20
    »:
    0.18
     کو
    0.18
    نگ
    0.18
    :**
    0.18
    ە
    0.18
     wzgl
    0.18
    Activations Density 0.000%

    No Known Activations