© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 148853
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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_18_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
    O
    0.51
    B
    0.50
    OK
    0.49
    冰
    0.49
     チェーン
    0.46
     miz
    0.46
    Code
    0.45
    板
    0.45
     Baseball
    0.45
    Baseball
    0.45
    POSITIVE LOGITS
    𝐝
    0.46
    ným
    0.46
     subordinated
    0.45
     آنچه
    0.44
     выгля
    0.44
    ény
    0.43
    ̉i
    0.42
    ívne
    0.42
     യൂണി
    0.42
     ذریع
    0.42
    Activations Density 0.000%

    No Known Activations