© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84803
    Prev
    Next
    INDEX
    Explanations

    acronyms and mnemonics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    0.45
     foreign
    0.42
    iced
    0.40
     외국
    0.40
    foreign
    0.39
    ↵
    0.39
    hr
    0.38
     étrangers
    0.38
    ↵↵↵
    0.38
    xspace
    0.37
    POSITIVE LOGITS
    韆
    0.43
    萬元
    0.42
    க்கமாக
    0.41
     සිදු
    0.40
    яна
    0.40
     কৃত
    0.39
    మం
    0.39
    ✾
    0.38
    蛩
    0.38
    辗
    0.38
    Activations Density 0.003%

    No Known Activations