© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216824
    Prev
    Next
    INDEX
    Explanations

    Is

    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_47_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
     ঘুমের
    0.41
    ggac
    0.40
     ਗ
    0.39
    ത്തിലെ
    0.37
     allait
    0.37
     গড়
    0.37
    屜
    0.36
     פע
    0.36
    गति
    0.36
     Indoor
    0.35
    POSITIVE LOGITS
     there
    1.37
    there
    1.23
    There
    1.22
     There
    1.21
     THERE
    1.20
     هناك
    1.16
     theres
    1.05
    THERE
    1.05
     वहाँ
    0.88
     есть
    0.84
    Activations Density 0.003%

    No Known Activations