© 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. 84921
    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
     ovviamente
    0.42
    sinh
    0.41
    SII
    0.41
    iser
    0.40
     essay
    0.39
    Mud
    0.38
     étapes
    0.38
    ꒪
    0.38
     steps
    0.37
    mgmt
    0.37
    POSITIVE LOGITS
     Recordings
    0.44
     Leafs
    0.43
    ással
    0.42
     Notices
    0.41
     Aircraft
    0.40
     Verkehr
    0.40
     Vacuum
    0.39
     Dying
    0.39
     Leaves
    0.39
     ке
    0.38
    Activations Density 0.000%

    No Known Activations