© 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. 149456
    Prev
    Next
    INDEX
    Explanations

    ongoing events and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     citizens
    0.42
    קת
    0.41
    钀
    0.40
     ಈಗಾಗಲೇ
    0.40
    齿
    0.40
    狧
    0.40
    ◼
    0.40
     extremists
    0.39
    élite
    0.39
     electors
    0.39
    POSITIVE LOGITS
    Light
    0.43
     Steinberg
    0.42
    H
    0.40
    Talk
    0.39
    noc
    0.39
    Inline
    0.39
    Tau
    0.39
     Light
    0.38
    lightbox
    0.38
    小便
    0.38
    Activations Density 0.000%

    No Known Activations