© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13067
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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_40_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
     dedi
    0.39
    哚
    0.39
    商品説明
    0.37
     पद्धतीने
    0.36
    埼玉県
    0.36
     subalgebra
    0.36
     Zane
    0.36
     इसरो
    0.35
     compréhension
    0.35
    ="*"
    0.35
    POSITIVE LOGITS
    meed
    0.40
    cred
    0.40
     Est
    0.40
     Annie
    0.39
    Annie
    0.39
     sticky
    0.39
    stom
    0.38
    ried
    0.37
     APC
    0.37
    স্ত
    0.36
    Activations Density 0.065%

    No Known Activations