© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74685
    Prev
    Next
    INDEX
    Explanations

    existing dictionary values

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ക്കളെ
    0.25
    𝒍
    0.25
     lớn
    0.24
    thi
    0.24
    lyk
    0.24
    ordin
    0.24
    ိမ်
    0.24
     থ
    0.23
    𝐥
    0.23
    ⼦
    0.23
    POSITIVE LOGITS
     اقد
    0.30
    Prim
    0.28
     Mam
    0.26
    Fprintf
    0.26
    Mel
    0.26
    symmetry
    0.26
     symmetry
    0.26
    Perfect
    0.25
    Miller
    0.25
    STRUCTION
    0.25
    Activations Density 0.004%

    No Known Activations