© 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. 58650
    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
    Y
    1.34
    För
    1.15
    '
    1.13
    E
    1.04
                    
    1.01
             
    0.97
    Untuk
    0.97
    ადა
    0.97
           
    0.96
     by
    0.96
    POSITIVE LOGITS
    t
    2.25
    s
    1.43
    f
    1.43
    س
    1.42
    d
    1.40
     for
    1.34
    ina
    1.34
    r
    1.31
    с
    1.25
    n
    1.22
    Activations Density 0.000%

    No Known Activations