© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106411
    Prev
    Next
    INDEX
    Explanations

    diamonds and zebras

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     occupying
    0.39
     интеллектуа
    0.38
    лос
    0.37
     Eti
    0.37
     Angkor
    0.37
     Puente
    0.36
    <li>
    0.36
     தூசி
    0.36
    ۟
    0.36
    amian
    0.35
    POSITIVE LOGITS
     Diamond
    0.51
     diamond
    0.47
    Diamond
    0.47
    diamond
    0.45
     Zebra
    0.44
    Diamonds
    0.43
     zebra
    0.42
    Gold
    0.42
     painting
    0.41
     zeb
    0.40
    Activations Density 0.013%

    No Known Activations