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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261165
    Prev
    Next
    INDEX
    Explanations

    studies show

    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
    ل
    1.23
    لک
    1.20
     ﺍﻟ
    1.15
    0
    1.14
    buyers
    1.13
    and
    1.10
     активности
    1.09
    3
    1.07
    ۰
    1.07
    ul
    1.05
    POSITIVE LOGITS
    ’
    1.40
    يت
    1.09
    '
    1.03
    ва
    1.02
    ้
    1.00
    (
    0.95
    <0xB7>
    0.93
    ี
    0.91
    ]
    0.88
    <0xA7>
    0.88
    Activations Density 0.004%

    No Known Activations