© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198391
    Prev
    Next
    INDEX
    Explanations

    country inaugurations

    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_46_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
     ahead
    0.52
    ahead
    0.45
     Ahead
    0.41
    Ahead
    0.41
     ऑपरेशन
    0.37
    න්නේ
    0.36
    砥
    0.35
    คืน
    0.35
    logram
    0.34
     пред
    0.34
    POSITIVE LOGITS
     day
    0.49
     giorno
    0.46
     день
    0.44
     päiv
    0.44
    anken
    0.44
     தினம்
    0.39
    日
    0.39
    enchen
    0.38
    event
    0.38
     event
    0.37
    Activations Density 0.001%

    No Known Activations