© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32847
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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_50_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
    ヴァン
    0.40
     एचडी
    0.38
     পাই
    0.38
     स्पॉट
    0.37
    빈
    0.37
    Avant
    0.36
    Nj
    0.36
     কথায়
    0.36
     এইচডি
    0.35
    লাইট
    0.35
    POSITIVE LOGITS
     M
    0.45
     Liao
    0.44
     Rayleigh
    0.42
     Xiao
    0.41
    iel
    0.40
     राह
    0.40
    لاست
    0.40
     Lu
    0.40
     derby
    0.38
     Romeo
    0.38
    Activations Density 0.000%

    No Known Activations