© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213571
    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_43_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
    ϡ
    0.46
    যান
    0.42
     சுரே
    0.40
    坩
    0.40
    zeniu
    0.39
    ర్టు
    0.39
    IME
    0.38
     देवता
    0.38
     Christi
    0.38
    𝖒
    0.38
    POSITIVE LOGITS
     lingers
    0.40
    geq
    0.38
    begin
    0.38
     ->
    0.37
    leftarrow
    0.37
    produ
    0.36
     offenses
    0.36
    oselect
    0.36
    ={()
    0.35
     linger
    0.35
    Activations Density 0.000%

    No Known Activations