© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22194
    Prev
    Next
    INDEX
    Explanations

    buildings and architecture

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    さ
    0.69
     さ
    0.57
    さと
    0.47
     са
    0.47
    สา
    0.46
    са
    0.45
    さは
    0.45
    Sa
    0.40
     سا
    0.38
    сад
    0.38
    POSITIVE LOGITS
     conv
    1.81
     Conv
    1.37
    conv
    1.32
    Conv
    1.29
     ab
    1.19
     cat
    1.13
     chap
    1.00
     убе
    0.86
     cl
    0.86
     convince
    0.77
    Activations Density 0.064%

    No Known Activations