© 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. 198514
    Prev
    Next
    INDEX
    Explanations

    amino

    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
    💊
    0.41
    URNIZ
    0.40
    garan
    0.37
    getSign
    0.36
    ，“
    0.35
    Carlton
    0.35
    窰
    0.34
    herin
    0.34
    diaz
    0.34
    🦷
    0.34
    POSITIVE LOGITS
    Virus
    0.43
     Viol
    0.41
     Vie
    0.40
     cadáver
    0.39
     मृ
    0.38
     Virus
    0.38
     Víctor
    0.38
     italian
    0.37
     Vi
    0.36
     virus
    0.36
    Activations Density 0.001%

    No Known Activations