© 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. 89136
    Prev
    Next
    INDEX
    Explanations

    listening to music

    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
     Anatom
    0.43
     child
    0.41
    child
    0.38
     UX
    0.36
    *>
    0.36
    fileID
    0.36
     компо
    0.36
    GameState
    0.36
     młod
    0.36
     निहित
    0.36
    POSITIVE LOGITS
     './
    0.38
     áng
    0.37
    .):
    0.36
     STARTED
    0.36
     stoichiometric
    0.36
     bootstrapping
    0.35
     Milling
    0.35
     logarith
    0.35
    бурга
    0.35
    ರಿ
    0.34
    Activations Density 0.006%

    No Known Activations