© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49438
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    𝖚
    0.41
     dilated
    0.39
     thymus
    0.38
     Futures
    0.37
    Substituting
    0.37
    രിച്ചി
    0.37
    اہد
    0.37
    电路
    0.36
    conditionals
    0.36
    ๑
    0.36
    POSITIVE LOGITS
     organisers
    0.45
     सकते
    0.43
     வேண்டிய
    0.42
    வதில்
    0.42
    ాలను
    0.41
    ሉ።
    0.40
    어야
    0.39
    ण्याचा
    0.38
    시는
    0.38
    줘야
    0.37
    Activations Density 0.000%

    No Known Activations