© 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. 357
    Prev
    Next
    INDEX
    Explanations

    default behaviors and settings

    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
    apunov
    0.46
     oggetti
    0.43
    भोग
    0.38
     पुर
    0.38
     Neuron
    0.38
     objetos
    0.37
    呫
    0.37
     oggetto
    0.36
     dvara
    0.36
    शिक्ष
    0.36
    POSITIVE LOGITS
    绞
    0.34
     distinct
    0.33
    Ranges
    0.33
    distinct
    0.33
    prac
    0.32
    rop
    0.31
    Hide
    0.31
    withdraw
    0.31
     discriminated
    0.31
    intl
    0.31
    Activations Density 0.008%

    No Known Activations