© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151607
    Prev
    Next
    INDEX
    Explanations

    balancing, focusing, categorized

    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_23_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
    för
    0.19
     "."
    0.19
    व्ह
    0.18
     Nikol
    0.18
     Tiếp
    0.18
     Ignore
    0.18
    🔘
    0.17
     İli
    0.17
    amalla
    0.17
     Baseline
    0.17
    POSITIVE LOGITS
     लेकिन
    0.20
     असली
    0.20
    債
    0.19
     rpg
    0.17
    tv
    0.17
    ненко
    0.17
    ד
    0.17
     কিন্তু
    0.17
     जोशी
    0.17
    Cohen
    0.17
    Activations Density 0.005%

    No Known Activations