© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 105114
    Prev
    Next
    INDEX
    Explanations

    Much

    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_44_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
     soap
    0.39
     recruitment
    0.39
     backdoor
    0.38
     palust
    0.38
     Keystone
    0.37
    ະຍ
    0.37
     trache
    0.37
    炊
    0.36
     blackmail
    0.36
    钰
    0.36
    POSITIVE LOGITS
    notify
    0.44
    wah
    0.44
    Вели
    0.42
    Kingdom
    0.41
    Widget
    0.40
    vať
    0.40
    Milan
    0.39
    warts
    0.38
    Status
    0.38
    Notify
    0.38
    Activations Density 0.000%

    No Known Activations