© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213929
    Prev
    Next
    INDEX
    Explanations

    fibers, invasion, perineal

    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
    <0x80>
    1.08
    ﻏ
    0.83
    ﻲ
    0.82
    ি
    0.81
     bă
    0.77
     dolayı
    0.77
     જ્યારે
    0.77
     في
    0.77
     incentivize
    0.76
     પરંતુ
    0.75
    POSITIVE LOGITS
    ב
    1.58
    ਰ
    1.42
     to
    1.32
    ک
    1.24
    전
    1.22
    은
    1.21
    هم
    1.19
    ่
    1.18
    to
    1.16
    ل
    1.16
    Activations Density 0.000%

    No Known Activations