© 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. 214247
    Prev
    Next
    INDEX
    Explanations

    maternity clothes and leave

    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
    </h4>
    1.23
    '
    1.21
    اک
    1.16
    нда
    1.12
    ا
    1.12
    の新
    1.11
    ень
    1.09
    تها
    1.09
    aarr
    1.09
    の高い
    1.09
    POSITIVE LOGITS
    í
    1.48
     o
    1.41
    j
    1.34
    ü
    1.32
    s
    1.23
     hoge
    1.20
    m
    1.18
    ă
    1.16
    ru
    1.16
    I
    1.13
    Activations Density 0.000%

    No Known Activations