© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32707
    Prev
    Next
    INDEX
    Explanations

    verbal, emocional, civil, mental, econômico, dual, locales, político, accidental, moral

    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_7_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
    an
    0.34
    <0x0D>
    0.29
    at
    0.28
    t
    0.27
    as
    0.27
    ad
    0.26
    т
    0.25
    ت
    0.24
     viele
    0.23
    ed
    0.23
    POSITIVE LOGITS
    )
    0.22
    ва
    0.20
    ]
    0.19
    ）
    0.19
    。
    0.19
    ])
    0.19
    ሰው
    0.18
     of
    0.18
     supplementation
    0.18
    ainkan
    0.17
    Activations Density 0.066%

    No Known Activations