© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18147
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     valve
    0.39
     appointments
    0.39
     font
    0.39
     textAppearance
    0.38
    竊
    0.37
     hatch
    0.37
     Appointments
    0.37
     typeface
    0.37
     Wordsworth
    0.36
     kits
    0.36
    POSITIVE LOGITS
    ppro
    0.40
    벡
    0.39
    romyalgia
    0.36
    EXPER
    0.36
    atenin
    0.35
    emf
    0.35
    ennan
    0.35
    Distribution
    0.35
    压力
    0.35
    룺
    0.34
    Activations Density 0.000%

    No Known Activations