© 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. 148733
    Prev
    Next
    INDEX
    Explanations

    how something is managed or achieved

    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
     কবি
    0.41
    दोनों
    0.41
     zwei
    0.41
     परिचित
    0.39
    琇
    0.39
     preserve
    0.39
    ెండు
    0.38
     gusts
    0.38
    ieten
    0.38
     drugih
    0.38
    POSITIVE LOGITS
    reflected
    0.38
     northward
    0.38
     reflected
    0.38
    Suff
    0.37
    prepend
    0.37
    んですけど
    0.37
    <0x88>
    0.37
     აღ
    0.36
     tessel
    0.36
    widehat
    0.36
    Activations Density 0.001%

    No Known Activations