© 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. 210618
    Prev
    Next
    INDEX
    Explanations

    soft mommy girlfriend

    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
     individuo
    1.52
     ajustar
    1.41
     campe
    1.36
     especiales
    1.36
     construido
    1.35
     requisitos
    1.33
    <0x0D>
    1.30
     obten
    1.30
     predom
    1.30
     assegn
    1.30
    POSITIVE LOGITS
    า
    1.69
    I
    1.66
    ong
    1.60
    it
    1.42
    uk
    1.41
    ü
    1.40
    is
    1.38
    au
    1.37
    ai
    1.32
     व
    1.31
    Activations Density 0.001%

    No Known Activations