© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76067
    Prev
    Next
    INDEX
    Explanations

    hashtags and category labels

    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_31_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
    紫色
    0.42
    🥔
    0.41
    蓝色
    0.40
    oscope
    0.39
    🥑
    0.38
    اصمة
    0.38
     sparkling
    0.37
    도시
    0.37
    inisc
    0.37
    空间的
    0.37
    POSITIVE LOGITS
     cancer
    0.38
    -------
    0.37
    She
    0.37
    ROWN
    0.37
    yticks
    0.37
     Yankee
    0.35
    ynt
    0.35
    ý
    0.35
     taxation
    0.35
    yclerView
    0.35
    Activations Density 0.001%

    No Known Activations