© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2666
    Prev
    Next
    INDEX
    Explanations

    code as

    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
     entering
    0.44
     {{
    0.44
    入れる
    0.43
     entry
    0.41
     넣
    0.40
     دخل
    0.39
     enters
    0.39
     inserted
    0.38
    {
    0.38
        
    0.38
    POSITIVE LOGITS
    ertain
    0.40
     eigenstates
    0.40
     meth
    0.38
    esson
    0.38
     Meth
    0.37
     個
    0.37
    Meth
    0.37
    amah
    0.37
    PropertyChanged
    0.36
    קת
    0.36
    Activations Density 0.014%

    No Known Activations