© 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. 261204
    Prev
    Next
    INDEX
    Explanations

    natural language, remedies, killer, sweeteners, polymers

    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
    )
    1.58
    ]
    1.38
     a
    1.27
    де
    1.27
    то
    1.24
    <0x80>
    1.23
    ै
    1.22
     )
    1.17
    ि
    1.15
     for
    1.13
    POSITIVE LOGITS
    s
    1.73
    ల
    1.33
    م
    1.12
    お子
    1.08
    ன
    1.08
    ன்
    1.07
    ન
    1.04
     devrez
    1.03
    सि
    1.02
    ar
    1.01
    Activations Density 0.002%

    No Known Activations