© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84563
    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_23_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
    ία
    0.51
     I
    0.47
     =
    0.45
    itt
    0.45
    उत्
    0.45
    casters
    0.44
    TMP
    0.44
    tex
    0.44
    uters
    0.44
     exceptions
    0.44
    POSITIVE LOGITS
     Labrenzia
    0.51
     பெண்களுக்கு
    0.47
    ெடு
    0.44
    >")
    0.44
    isSignedIn
    0.43
     élarg
    0.43
     Сьогодні
    0.43
    oljš
    0.43
    খেজুর
    0.43
    FBSDKInternal
    0.43
    Activations Density 0.000%

    No Known Activations