© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85486
    Prev
    Next
    INDEX
    Explanations

    exists( or isfile(

    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_18_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
     télé
    0.38
    釹
    0.38
    瑆
    0.34
    çuk
    0.33
    뚝
    0.33
    㮔
    0.33
     définitive
    0.33
     Zuge
    0.32
     cookbooks
    0.32
    ុល
    0.32
    POSITIVE LOGITS
    va
    0.40
     We
    0.39
    We
    0.39
    hay
    0.38
    history
    0.36
    from
    0.36
     substantially
    0.34
    ored
    0.34
    },
    0.34
     Medica
    0.34
    Activations Density 0.005%

    No Known Activations