© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19826
    Prev
    Next
    INDEX
    Explanations

    He has to

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    яз
    0.21
    ออกมา
    0.21
    새
    0.20
    뮤
    0.20
    오늘
    0.20
    이자
    0.19
    ین
    0.18
    وكان
    0.18
    摑
    0.18
    도는
    0.18
    POSITIVE LOGITS
    >]
    0.24
    ⟩
    0.22
    》
    0.22
    }}
    0.22
    ]].
    0.21
     AdWords
    0.21
    ]
    0.21
    OWER
    0.20
     ን
    0.20
     ]
    0.20
    Activations Density 0.001%

    No Known Activations