© 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. 90020
    Prev
    Next
    INDEX
    Explanations

    code block structure endings

    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
    embark
    0.42
    cant
    0.39
    넓
    0.39
    zion
    0.38
    ྱ
    0.37
    eu
    0.37
     gmin
    0.37
    nih
    0.37
     patiently
    0.36
     superviv
    0.36
    POSITIVE LOGITS
     phonons
    0.42
     घटना
    0.39
     disclosed
    0.39
    ofa
    0.39
    匿
    0.39
    Nobody
    0.38
     فريبي
    0.38
     Everybody
    0.38
     prank
    0.38
    PHONE
    0.38
    Activations Density 0.001%

    No Known Activations