© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198049
    Prev
    Next
    INDEX
    Explanations

    MOSS sales and provisions

    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_12_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
    itsky
    0.44
    VM
    0.42
     ويب
    0.41
    //!
    0.40
    Paxos
    0.40
    ugawa
    0.39
    VS
    0.39
    UGH
    0.39
    smooth
    0.38
    MSBuild
    0.38
    POSITIVE LOGITS
     chiese
    0.48
     Chimie
    0.47
     стоимости
    0.47
     Corn
    0.46
    '
    0.46
     montant
    0.44
     crise
    0.43
    áte
    0.43
     âng
    0.43
    ți
    0.42
    Activations Density 0.000%

    No Known Activations