© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212980
    Prev
    Next
    INDEX
    Explanations

    InfluxDB

    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_5_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
    1.52
    an
    1.45
    ↵
    1.32
     to
    1.13
    ación
    1.10
    一定的
    1.08
    <0x80>
    1.02
    ers
    1.02
    :
    1.02
    ische
    1.00
    POSITIVE LOGITS
    is
    1.23
    نوان
    1.23
    isinin
    1.19
    یا
    1.15
     Бүгенге
    1.14
     По
    1.13
    ية
    1.13
    リ
    1.13
    ﻧ
    1.12
     ಜ
    1.10
    Activations Density 0.000%

    No Known Activations