© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96918
    Prev
    Next
    INDEX
    Explanations

    icons like :rocket: or :bar_chart:

    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_14_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
     gỗ
    0.19
    신의
    0.18
     샤
    0.18
     ICM
    0.18
     보호
    0.18
     svojih
    0.18
     mantém
    0.18
     hals
    0.18
    commonByteArray
    0.18
     bảo
    0.18
    POSITIVE LOGITS
    ­
    0.17
    ¬
    0.17
    <start_of_image>
    0.16
     inex
    0.16
     вовсе
    0.15
     Center
    0.15
    otti
    0.15
     impacts
    0.15
     poor
    0.15
     frustrated
    0.15
    Activations Density 0.004%

    No Known Activations