© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133658
    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_50_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
     দশ
    0.41
     HDL
    0.38
    произ
    0.38
    祸
    0.38
     Peralta
    0.37
     VLAN
    0.37
     Voraus
    0.36
     produziert
    0.36
    ್ರಾ
    0.36
    Proc
    0.35
    POSITIVE LOGITS
    㛣
    0.42
    ChromeDriver
    0.42
     Allan
    0.40
    Allan
    0.40
    ție
    0.38
    зне
    0.38
    <unused40>
    0.38
    บ้าง
    0.37
    ije
    0.37
    Spectral
    0.37
    Activations Density 0.000%

    No Known Activations