© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 166623
    Prev
    Next
    INDEX
    Explanations

    mol

    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
     sub
    0.57
     przeciw
    0.49
    對
    0.44
    sub
    0.42
     đối
    0.42
     对
    0.41
    对
    0.40
    នា
    0.39
    র্থ
    0.38
     fub
    0.38
    POSITIVE LOGITS
    ോഗ
    0.40
    ontas
    0.37
    rop
    0.35
     وسی
    0.34
    handler
    0.34
    viewModel
    0.34
    layer
    0.34
     ماشي
    0.34
    噻
    0.34
    Ref
    0.34
    Activations Density 0.000%

    No Known Activations