© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61163
    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_2_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
    ח
    1.11
    UT
    1.02
     as
    1.00
     to
    0.99
     is
    0.98
    AA
    0.95
    ORE
    0.93
    Ü
    0.93
    其
    0.91
    টি
    0.91
    POSITIVE LOGITS
    dır
    1.17
     numeros
    1.10
    tive
    1.07
    dimensionality
    1.06
    tól
    1.04
    t
    1.03
    <0x80>
    1.02
    amard
    1.02
    ne
    1.00
    etl
    0.98
    Activations Density 0.000%

    No Known Activations