© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148501
    Prev
    Next
    INDEX
    Explanations

    guidelines

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    the acronym "EEAT" or "EAT".

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    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
    𝘺
    0.47
     domanda
    0.45
    سٹم
    0.45
    omain
    0.43
    টারি
    0.43
    Domain
    0.42
     rebuttal
    0.42
    cstr
    0.42
    سطس
    0.42
    yst
    0.41
    POSITIVE LOGITS
    ﺔ
    0.49
     coolest
    0.49
     winner
    0.47
     assertEquals
    0.46
     cùng
    0.43
    י
    0.43
     businessman
    0.43
    hur
    0.43
     ASME
    0.43
     資
    0.43
    Activations Density 0.000%

    No Known Activations