© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35829
    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_11_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
    a
    0.75
    at
    0.68
    e
    0.66
    er
    0.64
    on
    0.59
    k
    0.59
    mission
    0.58
    and
    0.58
    ke
    0.57
    he
    0.57
    POSITIVE LOGITS
     Automatically
    0.52
     판
    0.51
    ++]
    0.51
    tpVar
    0.50
     어려
    0.49
     Argu
    0.49
    㿝
    0.49
     względu
    0.49
     subsequently
    0.48
     TouchUtils
    0.48
    Activations Density 0.000%

    No Known Activations