© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141473
    Prev
    Next
    INDEX
    Explanations

    Honda cars

    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_46_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
    👳
    0.38
    Montana
    0.38
    顓
    0.37
     verbunden
    0.37
     NOVA
    0.37
     nova
    0.36
    Virginia
    0.36
    🐑
    0.36
     Montana
    0.36
    旗下
    0.36
    POSITIVE LOGITS
     Accord
    0.55
     accord
    0.52
     concord
    0.52
     Concord
    0.50
    Accord
    0.49
     Agreement
    0.47
    agreement
    0.47
     Acuerdo
    0.46
     acord
    0.46
    一致
    0.45
    Activations Density 0.000%

    No Known Activations