© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141213
    Prev
    Next
    INDEX
    Explanations

    configuration.nix system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    er
    0.53
     {
    0.53
     vulnerabilities
    0.53
     Arctic
    0.52
    ophagus
    0.52
                                
    0.51
     remodeled
    0.51
                
    0.51
     Utils
    0.51
     …
    0.50
    POSITIVE LOGITS
     আবু
    0.59
    𝑜
    0.53
    钎
    0.52
    Nếu
    0.49
     سير
    0.48
     ለአ
    0.48
    火焰
    0.48
    Jika
    0.47
    ولي
    0.47
    如有
    0.47
    Activations Density 0.006%

    No Known Activations