© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11721
    Prev
    Next
    INDEX
    Explanations

    convinced, intent, content

    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_13_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
     first
    0.55
     First
    0.55
    3
    0.55
     seconde
    0.55
    d
    0.54
     eerste
    0.52
     بخير
    0.52
    t
    0.52
    5
    0.52
    ﻱ
    0.52
    POSITIVE LOGITS
    ח
    0.54
    วก
    0.54
    ,\\
    0.53
    واره
    0.52
     hidup
    0.52
     ответствен
    0.52
     방식으로
    0.51
    mathbb
    0.51
    ிகளை
    0.51
    irond
    0.50
    Activations Density 0.031%

    No Known Activations