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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44138
    Prev
    Next
    INDEX
    Explanations

    meat types

    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_13_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
     intact
    0.42
     undamaged
    0.41
     unscathed
    0.39
     unharmed
    0.38
     l
    0.34
     alive
    0.32
     unbroken
    0.32
     vollständ
    0.31
    asis
    0.30
     Hass
    0.30
    POSITIVE LOGITS
    은
    0.31
    Cl
    0.31
    </h5>
    0.30
    Chevron
    0.30
    PL
    0.29
    Career
    0.29
    Lead
    0.29
    лся
    0.29
     вед
    0.28
    s
    0.28
    Activations Density 0.016%

    No Known Activations