© 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. 111596
    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
    nics
    1.05
    nings
    1.00
    :
    0.94
    ,
    0.93
    .
    0.92
    usions
    0.91
    럼
    0.90
    ]}
    0.87
    offs
    0.87
    nél
    0.87
    POSITIVE LOGITS
    t
    1.45
    א
    1.25
     powied
    1.23
    સ
    0.95
    έ
    0.95
     něk
    0.94
     Đ
    0.92
    <0x80>
    0.90
    N
    0.90
     człowieka
    0.89
    Activations Density 0.000%

    No Known Activations