© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208430
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     pushing
    0.42
    鲫
    0.41
     bending
    0.36
     besonderen
    0.35
     проде
    0.35
    пас
    0.35
    chengladbach
    0.35
    鯽
    0.34
     तमाम
    0.34
     کیس
    0.34
    POSITIVE LOGITS
    sdk
    0.36
    Sham
    0.36
     Bre
    0.36
     SDK
    0.35
     aram
    0.35
     Pharmac
    0.35
     حلق
    0.34
     Ec
    0.34
    alı
    0.34
    ন্ট
    0.34
    Activations Density 0.000%

    No Known Activations