© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110197
    Prev
    Next
    INDEX
    Explanations

    relish or words ending in ish

    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_2_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
    த்தில்
    1.10
     밝혔
    1.06
    ал
    1.01
    ay
    1.00
     написа
    0.96
    0
    0.96
    но
    0.93
    ۰
    0.92
     некоторые
    0.91
    ০০
    0.88
    POSITIVE LOGITS
    re
    1.32
    )
    1.29
    dan
    1.16
    ل
    1.13
    ),
    1.13
    ],
    1.12
    s
    1.10
    دا
    1.09
    d
    1.09
    、
    1.09
    Activations Density 0.000%

    No Known Activations