© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119606
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
     menikah
    0.41
    婚
    0.39
     결혼
    0.38
     Colt
    0.38
    ฏิ
    0.36
    帖子
    0.35
    柜
    0.35
    众多
    0.35
    第
    0.35
    一流
    0.35
    POSITIVE LOGITS
    वरिश
    0.45
     longitudinale
    0.45
     Geografia
    0.44
     সর্বনাশ
    0.43
     downsides
    0.43
    デメリット
    0.42
     drawbacks
    0.41
     punishments
    0.41
     hierarch
    0.41
     manipulations
    0.40
    Activations Density 0.000%

    No Known Activations