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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215190
    Prev
    Next
    INDEX
    Explanations

    cry or study

    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
    on
    1.64
    to
    1.38
    m
    1.38
    ב
    1.38
    도
    1.30
    p
    1.30
    자
    1.30
    전
    1.28
    re
    1.21
    де
    1.19
    POSITIVE LOGITS
    ↵
    1.24
    و
    1.13
     Statue
    1.05
    </strong>
    1.04
    ]
    1.03
    د
    1.02
    </h3>
    0.99
     V
    0.99
     l
    0.98
     Titanic
    0.97
    Activations Density 0.008%

    No Known Activations