© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209722
    Prev
    Next
    INDEX
    Explanations

    absorber

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     Mitochond
    0.42
     thickly
    0.39
     nan
    0.37
     mitochondria
    0.37
     રમ
    0.36
    挈
    0.36
     Philosophical
    0.35
    쪘
    0.35
     NS
    0.35
     ವೆ
    0.35
    POSITIVE LOGITS
     absorber
    0.46
     absorbers
    0.42
    UMBIA
    0.42
    吸
    0.41
    უკ
    0.38
     považ
    0.38
    OLINA
    0.38
    ολ
    0.37
    absor
    0.37
    Gel
    0.37
    Activations Density 0.001%

    No Known Activations