© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177372
    Prev
    Next
    INDEX
    Explanations

    eroticism or adult content

    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_24_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
     செயலா
    0.42
     Entre
    0.40
     BY
    0.38
    Per
    0.37
     Anterior
    0.37
     Compañ
    0.37
    })=\
    0.36
    分泌
    0.36
     Natürlich
    0.36
    etz
    0.36
    POSITIVE LOGITS
     konte
    0.39
     contesto
    0.38
     context
    0.37
    context
    0.37
    RawContext
    0.34
    互
    0.34
     contexto
    0.34
     mutual
    0.33
    ábban
    0.32
     mú
    0.32
    Activations Density 0.020%

    No Known Activations