© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77962
    Prev
    Next
    INDEX
    Explanations

    Indonesian words

    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_53_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
     DX
    0.45
    innerApiCalls
    0.41
     Bioinformatics
    0.39
    चान
    0.39
     eo
    0.38
     ki
    0.37
     ken
    0.37
    泬
    0.37
     EZ
    0.37
     गेहूं
    0.36
    POSITIVE LOGITS
     kep
    0.75
     Kep
    0.68
    Kep
    0.62
    kep
    0.61
     ir
    0.53
     kem
    0.44
    bus
    0.44
     kek
    0.43
     s
    0.42
     bus
    0.42
    Activations Density 0.001%

    No Known Activations