© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45672
    Prev
    Next
    INDEX
    Explanations

    cryptocrystalline, Ishtar Gate, pseudomorph

    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_13_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
    }$
    0.14
    йн
    0.13
    نو
    0.13
     Govern
    0.12
    fold
    0.12
     Rag
    0.12
     Merchant
    0.12
     Steward
    0.12
     Victory
    0.12
    ↵
    0.12
    POSITIVE LOGITS
     acetyl
    0.18
    acetyl
    0.17
    Acetyl
    0.16
    ību
    0.15
    注意力
    0.15
     उत्पाद
    0.15
     भारता
    0.15
     ಸ
    0.14
    Javascript
    0.14
    der
    0.14
    Activations Density 0.003%

    No Known Activations