© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5942
    Prev
    Next
    INDEX
    Explanations

    small

    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_44_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
    hagen
    0.43
    csproj
    0.43
    veratrol
    0.38
    andran
    0.38
    烔
    0.37
     uitvo
    0.37
     Peki
    0.37
    beek
    0.36
    atherapy
    0.36
     Lek
    0.35
    POSITIVE LOGITS
    Small
    0.52
    SMALL
    0.47
     small
    0.47
     Small
    0.46
    小
    0.45
     pequeño
    0.44
     pequena
    0.43
    small
    0.43
     pequeña
    0.42
     kleinen
    0.42
    Activations Density 0.012%

    No Known Activations