© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 238908
    Prev
    Next
    INDEX
    Explanations

    opening quotation mark

    np_acts-logits-general · gemini-2.5-flash-lite

    end punctuation

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

    specific news details and factual reporting.

    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_25_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
     managable
    0.29
    ᐳ
    0.29
    介绍
    0.28
    
    0.28
     getMenuInflater
    0.27
    でしたが
    0.27
     UICtrl
    0.27
     소개
    0.26
    简介
    0.26
    nabi
    0.26
    POSITIVE LOGITS
     layers
    0.24
    layers
    0.23
    費
    0.23
      
    0.23
    ).
    0.23
    lz
    0.22
     scattering
    0.22
    LR
    0.22
    AP
    0.22
    loss
    0.22
    Activations Density 0.001%

    No Known Activations