© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44166
    Prev
    Next
    INDEX
    Explanations

    workarounds

    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_3_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
     soulful
    0.63
    ビ
    0.61
     visceral
    0.59
     standout
    0.59
     precession
    0.59
     quiescent
    0.59
     joyful
    0.58
     severe
    0.58
     branching
    0.57
     monumental
    0.56
    POSITIVE LOGITS
    <0x0D>
    0.87
    of
    0.67
    आती
    0.66
    ע
    0.65
    ١
    0.64
     artworks
    0.64
    v
    0.64
    Cryptography
    0.64
     are
    0.63
    вом
    0.63
    Activations Density 0.002%

    No Known Activations