© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121297
    Prev
    Next
    INDEX
    Explanations

    * that comes before *

    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_27_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
    顺序
    0.49
     zuerst
    0.48
     먼저
    0.47
    先
    0.45
    先に
    0.44
     primero
    0.44
    doğan
    0.42
    首先
    0.41
    inverse
    0.41
     sequentially
    0.41
    POSITIVE LOGITS
     velas
    0.38
    詎
    0.36
     „
    0.35
     Grac
    0.35
     Nantes
    0.34
     Vallée
    0.34
    стую
    0.34
     vias
    0.34
     pap
    0.33
     sed
    0.33
    Activations Density 0.033%

    No Known Activations