© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31662
    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_31_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
     quỹ
    0.39
    leduj
    0.35
    ▀
    0.35
    mem
    0.35
     թ
    0.34
    demir
    0.34
    accent
    0.34
    ercase
    0.33
    resonant
    0.33
    टीन
    0.33
    POSITIVE LOGITS
     methodological
    0.42
     United
    0.41
     cucumber
    0.41
     susceptibility
    0.40
     motorists
    0.40
    ]));
    0.39
     SEARCH
    0.38
     fertilizers
    0.38
     Cancellation
    0.38
     methodologies
    0.38
    Activations Density 0.000%

    No Known Activations