© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76990
    Prev
    Next
    INDEX
    Explanations

    you might need

    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
    疸
    0.39
     সরাসরি
    0.38
    state
    0.37
     Laos
    0.37
    ignor
    0.37
     Milne
    0.37
     infuri
    0.36
     condol
    0.36
     coffee
    0.36
     LA
    0.36
    POSITIVE LOGITS
    ៅ
    0.39
    ু
    0.38
    珂
    0.36
    ≒
    0.35
     व्यापक
    0.35
    }^{*}=\
    0.35
    usional
    0.34
    brevi
    0.34
    ">→</
    0.34
    ありが
    0.33
    Activations Density 0.007%

    No Known Activations