© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 300
    Prev
    Next
    INDEX
    Explanations

    state management concepts

    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_40_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
     vectorize
    0.41
     октября
    0.37
    Hare
    0.37
    astudio
    0.37
    连续
    0.37
    यां
    0.37
    пон
    0.36
     ሂ
    0.36
    릿
    0.36
    SequentialGroup
    0.36
    POSITIVE LOGITS
     Apple
    0.51
     Fire
    0.43
     Chad
    0.42
     Puro
    0.41
     shared
    0.41
     Cupertino
    0.41
     Mus
    0.41
    Apple
    0.41
     Mari
    0.40
     cuidados
    0.40
    Activations Density 0.006%

    No Known Activations