© 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. 104840
    Prev
    Next
    INDEX
    Explanations

    South Korean tech companies

    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
     Ανα
    0.45
     spitting
    0.40
    ⁧
    0.38
    হীন
    0.37
    нави
    0.37
    ក្ត
    0.37
    通
    0.37
     Chủ
    0.37
    islava
    0.36
    રે
    0.36
    POSITIVE LOGITS
    Marker
    0.40
    陂
    0.39
    ҹ
    0.39
     acabou
    0.38
    ;:
    0.38
    zględ
    0.38
    Divider
    0.37
    ocre
    0.37
    Markers
    0.37
     marker
    0.36
    Activations Density 0.000%

    No Known Activations