© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201555
    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_46_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
     ይጠ
    0.42
    룔
    0.42
    riture
    0.41
    kate
    0.41
    Kas
    0.40
     drives
    0.39
    Champ
    0.39
    Driving
    0.38
    rava
    0.38
     Limb
    0.38
    POSITIVE LOGITS
    ᱫ
    0.41
     bib
    0.38
    gele
    0.38
     ভু
    0.36
    odar
    0.35
    획
    0.35
    ため
    0.34
     સ્
    0.34
     convexo
    0.34
    uft
    0.34
    Activations Density 0.000%

    No Known Activations