© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 105255
    Prev
    Next
    INDEX
    Explanations

    central

    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
    hiyam
    0.39
    镛
    0.37
    间隔
    0.36
    Serv
    0.36
    objective
    0.36
     اللجنة
    0.36
     عادة
    0.36
    ICIAL
    0.36
    Gotham
    0.35
     бюд
    0.35
    POSITIVE LOGITS
     vaut
    0.43
     rad
    0.43
    linie
    0.42
     drifting
    0.41
    ভাগ
    0.40
    anes
    0.40
    மீ
    0.40
    ፏ
    0.39
     memang
    0.38
     OutputStream
    0.38
    Activations Density 0.001%

    No Known Activations