© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 105083
    Prev
    Next
    INDEX
    Explanations

    entities and organizations

    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
     ti
    0.41
     dissipation
    0.38
    ང་
    0.36
    țe
    0.35
     TIP
    0.35
    iece
    0.35
    ው
    0.35
     SET
    0.34
    ამართ
    0.34
     উইল
    0.34
    POSITIVE LOGITS
    ಿಕೊಂಡು
    0.42
     Juin
    0.38
     sn
    0.37
     dens
    0.37
    」（
    0.37
     cadeira
    0.37
     hib
    0.36
     κ
    0.36
    哽
    0.36
    十二
    0.36
    Activations Density 0.000%

    No Known Activations